SlideShare a Scribd company logo
1 of 152
Anime Generation with AI
Koichi Hamada
AI Unit, DeNA Co., Ltd., Tokyo, Japan
Anime Inbetweening with SPGAN
Anime Generation with PSGAN
AGENDA
Recent Progress on Image Generation and Issues
Conclusion
- Anime Generation with AI -
Overview
Our Approaches and Contributions
Other AI Solutions for Anime Production Issues
Anime Inbetweening with SPGAN
Anime Generation with PSGAN
AGENDA
Recent Progress on Image Generation and Issues
Conclusion
- Anime Generation with AI -
Overview
Our Approaches and Contributions
Other AI Solutions for Anime Production Issues
AI Generated Anime Inbetweening on Zunda Horizon* Test Data**
Input Frames AI Generated Frames
(x16 Generation)
AI anime inbetweening for a wide variety of objects
**Trained using DeNA Dataset which does not include “Zunda Horizon” data*SSS STL WAO 2017 “Zunda Horizon”
Generated Anime: https://youtu.be/X9j1fwexK2c?t=4
AI Generated Anime Inbetweening on Zunda Horizon* Test Data**
AI Generated Frames
(x4 Generation)
Actual Frames
drawn by Human Animators
(x4 Generation)
Input Frames
Comparison with human animators
**Trained using DeNA Dataset which does not include “Zunda Horizon” data*SSS STL WAO 2017 “Zunda Horizon”
Generated Anime: https://youtu.be/X9j1fwexK2c?t=80
Anime Generation with DeNA AI
Generated Anime
4x4
4x4
1024x1024
4x4
4x4
Latent
Real Condition
1024x1024 1024x1024
1024x1024
512x512
512x512
1024x1024
Add animation to the new character
by imposing a pose sequence
Generation of brand new characters
Progressive Structure-conditional GANs (PSGAN)
Generated
Full-body High-resolution Anime Generation with Progressive Structure-conditional Generative Adversarial Networks.
Koichi Hamada, Kentaro Tachibana, Tianqi Li, Hiroto Honda, and Yusuke Uchida. In ECCV Workshop 2018.
Successful image generation of full-body and high-resolution characters
Diverse characters and anime generation
https://youtu.be/X9j1fwexK2c?t=104Generated Anime:
Successful video interpolation between frames with large structural movement
Anime inbetweening
Anime Generation with DeNA AI
Input SPGAN
(Ours)
SOTA model
Deep Voxel Flow
Structure-consistent Prediction GANs (SPGAN)
Deep Voxel Flow
(ICCV’17)
Deep Voxel Flow
(ICCV'17)
PSNR
SSIM
Structured displacement
SPGAN
(Ours)
SPGAN
(Ours)
Structural displacementStructural displacement
Challenges toward Anime Generation with Deep Generative Models.
Koichi Hamada and Tianqi Li. In DeNA TechCon 2019. https://youtu.be/X9j1fwexK2c?t=132Generated Anime:
Successful image generation with detailed textures for each structural element
Anime generation with a few images
Anime Generation with DeNA AI
Structural Feature-embedding GANs (SFGAN)
Rough designation
(Structure designation)
Generated
result
Rough designation
(Structure designation)
Generated
result
Image
(1 frame)
Image
(1 frame)
https://youtu.be/X9j1fwexK2c?t=166Generated Anime:
Successful landscape generation with designated detailed texture for each part
Background art generation
Anime Generation with DeNA AI
Structural Feature-embedding GANs (SFGAN)
Image (1 frame)
SFGAN
(Ours)Layout
SoTA model
SPADE (CVPR’19)
Generated Result
Successful colorization that exactly reflects color example and line details
Exact colorization based on colorized example
Anime Generation with DeNA AI
Colorized example (1 frame) Colorized resultLines Rough
Structural Feature-embedding GANs (SFGAN)
https://youtu.be/X9j1fwexK2c?t=191Generated Anime:
Structure-Aware Generative Learning
A key solution for these challenges
Anime Generation with DeNA AI
We propose:
In 2018, AI generates high-quality images hard to distinguish from real photos
Anime Generation
High-quality image generation
with complex structures
Progressive Structure-conditional GANs
(PSGAN)
Our
Solution
Challenge
Back-
ground
Structure-Aware Generative Learning
Successful generation of diverse characters and animations
Structure-consistent Prediction GANs
(SPGAN)
Progressive Structure-conditional GANs
(PSGAN)Structure-Aware Generative Learning
Anime Inbetweening
Interpolation between frames
with large structural movement
Anime Generation with DeNA AI
We will talk about:
- Progress and challenges in cutting-edge image generation
- A solution by DeNA AI’s Structure-Aware Generative Learning
Anime Generation with DeNA AI
2010 – ML for Games
Launched ML group at DeNA. Applied ML/DM to improve games
2011 – ML for the Gaming Platform ‘Mobage’ (51 million users)
Developed dozens of distributed ML systems for a game platform
2014 – present: ML for All Services at DeNA
Develop ML systems for a wide range of services
Social Network MangaGaming Platform ChatbotNews
Launched the Group for Machine Learning (ML) at DeNA in 2010
Have developed a broad range of services utilizing ML for over 9 years
Examples:
Koichi Hamada (@hamadakoichi)
Ph.D. in Theoretical Physics
(Quantum and Statistical Field Theory)
Book:
“Technologies that support the large-scale
social gaming platform Mobage”
(Best Book Award in CEDEC 2014)
Founder - TokyoWebmining Community (February 2010)
- Objective: Expand the fields of practical applications of Machine Learning
- 1,500 registered participants with over 60 organized meet-ups
Launched the Group for Machine Learning (ML) at DeNA in 2010
Have developed a broad range of services utilizing ML for over 9 years
Koichi Hamada (@hamadakoichi)
5. Design Interfaces
Service
Front End
2. Design User Experiences
4. Design Auto Refinement Cycles
3. Design Services
7. Design Distributed Algorithms
8. Implement Distributed Algorithms
Distributed
Back End
YARN
HDFS
GPU
1. Research and Develop AI Models
New Valuable User Experiences
My activities:
Have designed and developed
new valuable experiences and services utilizing AI
Koichi Hamada (@hamadakoichi)
6. Design Logging
Designs, Implementations, Demonstration Experiments, Research Paper Publications,
Practical Applications, and Project Promotion
Generated Anime
Koichi Hamada (@hamadakoichi)
AI Anime Generation Project
AI Development and Project Lead
AI Generated Results for Anime Inbetweening on “Zunda Horizon*” Test Data**: https://youtu.be/X9j1fwexK2c?t=4
Input Frames AI Generated Frames
(x16 Generation)
**Trained using DeNA Dataset which does not include “Zunda Horizon” data*SSS STL WAO 2017 “Zunda Horizon”
Anime Inbetweening with SPGAN
Anime Generation with PSGAN
AGENDA
Recent Progress on Image Generation and Issues
Conclusion
- Anime Generation with AI -
Overview
Our Approaches and Contributions
Other AI Solutions for Anime Production Issues
Question: Which image was generated by AI?
1 3 5 7
2 4 6 8
Question: Which image was generated by AI?
Question: Which image was generated by AI?
AI
Real Photos
1 3 5 7
2 4 6 8
Answer: All of the top images
Question: Which image was generated by AI?
Answer: All of the top images
ProgressiveGAN (Karras et al., ICLR 2018) BigGAN (Brock et al., ICLR 2019)
1 3 5 7
2 4 6 8
AI
Real Photos
High-resolution and high-quality image generation by AI
AI-generated images have become higher resolution and quality
and are harder to distinguish from real photos
ProgressiveGAN (Karras et al., ICLR 2018) BigGAN (Brock et al., ICLR 2019)
High-resolution and high-quality image generation by AI
AI-generated images have become higher resolution and quality
and are harder to distinguish from real photos
ProgressiveGAN (Karras et al., ICLR 2018) BigGAN (Brock et al., ICLR 2019)
High-resolution and high-quality image generation by AI
AI-generated images have become higher resolution and quality
and are harder to distinguish from real photos
ProgressiveGAN (Karras et al., ICLR 2018) BigGAN (Brock et al., ICLR 2019)
Generative Adversarial Networks
(GANs)
Generator and Discriminator compete
and improve the generation quality
Generative Adversarial Networks (GANs)
Discriminator: classifies the input data as either real or fake
Generator: attempts to fool the Discriminator by generating realistic images
Generative Adversarial Nets.
Ian J. Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-
Farley, Sherjil Ozair, Aaron Courville, Yoshua Bengio.
arXiv:1406.2661. In NIPS 2014.
Generator and Discriminator compete
and improve the generation quality
Generative Adversarial Networks (GANs)
Minimax Objective function
Discriminator classifies
the real data as ‘real’
(Goodfellow+, NIPS2014, Deep Learning Workshop, Presentation)
Discriminator classifies
the generated data as ‘fake’
Discriminator tries to
classify correctly
(maximize)
Generator tries to fool Discriminator(minimize)
High-resolution and high-quality image generation with GANs
AI-generated images have become higher resolution and quality
and are harder to distinguish from real photos
ProgressiveGAN (Karras et al., ICLR 2018) BigGAN (Brock et al., ICLR 2019)
High-resolution and high-quality image generation with GANs
AI-generated images have become higher resolution and quality
and are harder to distinguish from real photos
ProgressiveGAN (Karras et al., ICLR 2018) BigGAN (Brock et al., ICLR 2019)
Progressive GAN (Karras+, ICLR'18)
Progressive growth of Generator and Discriminator
Stable generation of 1024 x 1024 images
Generated Images (1024X1024)
Generated Images (256x256)
Progressive Growing of GANs for Improved Quality, Stability, and Variation
Tero Karras, Timo Aila, Samuli Laine, Jaakko Lehtinen. In ICLR 2018.
https://youtu.be/XOxxPcy5Gr4?t=1m47s
Progressive Growing of GANs for Improved Quality, Stability, and Variation
Tero Karras, Timo Aila, Samuli Laine, Jaakko Lehtinen. In ICLR 2018.
Progressive GAN (Karras+, ICLR'18)
https://youtu.be/XOxxPcy5Gr4?t=4m
Progressive Growing of GANs for Improved Quality, Stability, and Variation
Tero Karras, Timo Aila, Samuli Laine, Jaakko Lehtinen. In ICLR 2018.
Progressive GAN (Karras+, ICLR'18)
High-resolution and high-quality image generation with GANs
AI-generated images have become higher resolution and quality
and are harder to distinguish from real photos
ProgressiveGAN (Karras et al., ICLR 2018) BigGAN (Brock et al., ICLR 2019)
High-resolution and high-quality image generation with GANs
AI-generated images have become higher resolution and quality
and are harder to distinguish from real photos
ProgressiveGAN (Karras et al., ICLR 2018) BigGAN (Brock et al., ICLR 2019)
BigGAN (Brock+, ICLR'19)
Class conditional image generation
Diverse and high-quality image generation using ImageNet
+ Spectral Normalization on Generator
+ Self Attention
+ Two Time Scale Update Rule
Generated Images (512x512)
+ Spectral Normalization on Discriminator
+ Projection Discriminator
SNGAN with Projection (Miyato+, ICLR’18)
SAGAN (Zhang+, 18)
BigGAN (Brock+, ICLR’19)
+ Large Batch Size (256→2048)
+ Large Channel (64→96)
+ Shared Embedding
+ Hierarchical Latent Space
+ Truncation Trick
+ Orthogonal Regularization
+ First Singular Value Clamp
+ Zero-centered Gradient Penalty
Large Scale GAN Training for High Fidelity Natural Image Synthesis.
Andrew Brock, Jeff Donahue, Karen Simonyan. arXiv:1809.11096. In ICLR 2018.
BigGAN (Brock+, ICLR'19)
Class conditional image generation
Diverse and high-quality image generation using ImageNet
Generator
Typical Architecture
Res Block
Architecture for ImageNet at 512x512
Large Scale GAN Training for High Fidelity Natural Image Synthesis.
Andrew Brock, Jeff Donahue, Karen Simonyan. arXiv:1809.11096. In ICLR 2019.
Generated Images (512x512)
BigGAN (Brock+, ICLR'19)
Large Scale GAN Training for High Fidelity Natural Image Synthesis.
Andrew Brock, Jeff Donahue, Karen Simonyan. arXiv:1809.11096. In ICLR 2019.
Generates high-fidelity and diverse images using ImageNet with 1000 classes
Generated Images (512x512)
BigGAN (Brock+, ICLR'19)
Large Scale GAN Training for High Fidelity Natural Image Synthesis.
Andrew Brock, Jeff Donahue, Karen Simonyan. arXiv:1809.11096. In ICLR 2019.
Generates high-fidelity and diverse images using ImageNet with 1000 classes
Generated Images (512x512)
BigGAN (Brock+, ICLR'19)
Large Scale GAN Training for High Fidelity Natural Image Synthesis.
Andrew Brock, Jeff Donahue, Karen Simonyan. arXiv:1809.11096. In ICLR 2019.
Generates high-fidelity and diverse images using ImageNet with 1000 classes
Generated Images (512x512)
BigGAN (Brock+, ICLR'19)
Large Scale GAN Training for High Fidelity Natural Image Synthesis.
Andrew Brock, Jeff Donahue, Karen Simonyan. arXiv:1809.11096. In ICLR 2019.
Generates high-fidelity and diverse images using ImageNet with 1000 classes
Generated Images (512x512)
BigGAN (Brock+, ICLR'19)
Generates high-fidelity and diverse images using ImageNet with 1000 classes
Generated Images (512x512)
Large Scale GAN Training for High Fidelity Natural Image Synthesis.
Andrew Brock, Jeff Donahue, Karen Simonyan. arXiv:1809.11096. In ICLR 2019.
BigGAN (Brock+, ICLR'19)
Large Scale GAN Training for High Fidelity Natural Image Synthesis.
Andrew Brock, Jeff Donahue, Karen Simonyan. arXiv:1809.11096. In ICLR 2019.
Generates high-fidelity and diverse images using ImageNet with 1000 classes
Generated Images (512x512)
BigGAN (Brock+, ICLR'19)
Large Scale GAN Training for High Fidelity Natural Image Synthesis.
Andrew Brock, Jeff Donahue, Karen Simonyan. arXiv:1809.11096. In ICLR 2019.
Generates high-fidelity and diverse images using ImageNet with 1000 classes
Generated Images (512x512)
High-resolution and high-quality image generation with GANs
ProgressiveGAN (Karras et al., ICLR 2018) BigGAN (Brock et al., ICLR 2019)
AI-generated images have become higher resolution and quality
and are harder to distinguish from real photos
High-resolution and high-quality image generation with GANs
AI-generated images have become higher resolution and quality
and are harder to distinguish from real photos
However, full-body image generation with complex structures has been a challenge
ProgressiveGAN (Karras et al., ICLR 2018) BigGAN (Brock et al., ICLR 2019)
High-resolution and high-quality image generation with GANs
ProgressiveGAN (Karras et al., ICLR 2018) BigGAN (Brock et al., ICLR 2019)
AI-generated images have become higher resolution and quality
and are harder to distinguish from real photos
However, full-body image generation with complex structures has been a challenge
High-resolution and high-quality image generation with GANs
ProgressiveGAN (Karras et al., ICLR 2018) BigGAN (Brock et al., ICLR 2019)
Applications for Anime Production
Limited to some specific cases, such as
- Generation for specific body parts (e.g. Face)
- Colorization (which does not treat structural generation)
AI-generated images have become higher resolution and quality
and are harder to distinguish from real photos
However, full-body image generation with complex structures has been a challenge
Anime Inbetweening with SPGAN
Anime Generation with PSGAN
AGENDA
Recent Progress on Image Generation and Issues
Conclusion
- Anime Generation with AI -
Overview
Our Approaches and Contributions
Other AI Solutions for Anime Production Issues
Anime Generation with DeNA AI
Generated Anime
4x4
4x4
1024x1024
4x4
4x4
Latent
Real Condition
1024x1024 1024x1024
1024x1024
512x512
512x512
1024x1024
Add animation to the new character
by imposing a pose sequence
Generation of brand new characters
Progressive Structure-conditional GANs (PSGAN)
Generated
Full-body High-resolution Anime Generation with Progressive Structure-conditional Generative Adversarial Networks.
Koichi Hamada, Kentaro Tachibana, Tianqi Li, Hiroto Honda, and Yusuke Uchida. In ECCV Workshop 2018.
Successful image generation of full-body and high-resolution characters
Diverse characters and anime generation
https://youtu.be/X9j1fwexK2c?t=104Generated Anime:
DeNA AI: Diverse Characters and Anime Generation
https://youtu.be/bIi5gSITK0EFull-body anime generation with Progressive Structure-conditional GANs
Generated results: Brand new characters
DeNA AI: Diverse Characters and Anime Generation
https://youtu.be/0LQlfkvQ3OkAdding action to full-body anime characters with Progressive Structure-conditional GANs
Can add animation to the new character
by specifying a sequence of 2D poses
Challenges toward Anime Generation with Deep Generative Models
Koichi Hamada and Tianqi Li. In DeNA TechCon 2019.
Successful video interpolation between frames with large structural movement
Anime inbetweening
DeNA AI: Anime Inbetweening
Structure-consistent Prediction GANs (SPGAN)
Input SPGAN
(Ours)
SOTA model
Deep Voxel Flow
Deep Voxel Flow
(ICCV’17)
Deep Voxel Flow
(ICCV'17)
PSNR
SSIM
Structured displacement
SPGAN
(Ours)
SPGAN
(Ours)
Structural displacementStructural displacement
https://youtu.be/X9j1fwexK2c?t=132Generated Anime:
DeNA AI: Anime Inbetweening
Can inbetween frames with large structural movement
(e.g. turning around)
Inbetweening of frames
with small movement
SOTA model
Deep Voxel FlowInput
SPGAN
(Ours)
Inbetweening of frames
with large movement
https://youtu.be/vXVr64BbXHYExperimental Results: “Anime Frame Generation with Structure-consistent Prediction GANs”
https://youtu.be/X9j1fwexK2c?t=139Video:
DeNA AI: Anime Inbetweening
step size = 1 step size = 4 step size = 7 step size = 10
Input
SPGAN
(Ours)
SoTA
Deep Voxel
Flow
(ICCV’17)
Can inbetween frames with large structural movement
with good structural and time consistency
Small Structural displacement Large
https://youtu.be/vXVr64BbXHYExperimental Results: “Anime Frame Generation with Structure-consistent Prediction GANs”
https://youtu.be/X9j1fwexK2c?t=150Video:
DeNA AI: Anime Inbetweening
Deep Voxel Flow Ours
Average PSNR/SSIM on test dataset (step size=4)
PSNR SSIM
Deep Voxel Flow 23.32 0.9294
SPGAN (Ours) 24.27 0.9407
SPGAN (Ours)
Can inbetween frames with large structural movement
with good structural and time consistency
PSNR
SSIM
Successful image generation with detailed textures for each structural element
Anime generation with a few images
DeNA AI: Anime generation with a few images
Structural Feature-embedding GANs (SFGAN)
Rough designation
(Structure designation)
Generated
result
Rough designation
(Structure designation)
Generated
result
Image
(1 frame)
Image
(1 frame)
https://youtu.be/X9j1fwexK2c?t=166Generated Anime:
Successful image generation with detailed textures for each structural element
Anime generation with a few images
DeNA AI: Anime generation with a few images
Can generate diverse body type, clothing, etc. with rough designation
Structural Feature-embedding GANs (SFGAN)
Rough designation
(Structure designation)
Generated
result
Rough designation
(Structure designation)
Generated
result
Image
(1 frame)
Image
(1 frame)
https://youtu.be/X9j1fwexK2c?t=166Generated Anime:
Successful landscape generation with designated detailed texture for each part
Background art generation
DeNA AI: Background art generation
Structural Feature-embedding GANs (SFGAN)
Image (1 frame)
SFGAN
(Ours)Layout
SoTA model
SPADE (CVPR’19)
Generated Result
Successful colorization that exactly reflects color example and line details
Exact colorization based on colorized example
DeNA AI: Exact colorization
Structural Feature-embedding GANs (SFGAN)
Colorized example (1 frame) Colorized resultLines Rough
https://youtu.be/X9j1fwexK2c?t=191Generated Anime:
Structure-Aware Generative Learning
DeNA AI
Development of AI Anime Generation
Anime Generation with DeNA AI
Structure-Aware Generative Learning
Successful generation of diverse characters and animations
Anime Generation with DeNA AI
Our
Solution
Challenge
Back-
ground
Structure-Aware Generative Learning
Successful generation of diverse characters and animations
In 2018, AI generates high-quality images hard to distinguish from real photos
Anime Generation with DeNA AI
Our
Solution
Challenge
Back-
ground
Structure-Aware Generative Learning
Successful generation of diverse characters and animations
In 2018, AI generates high-quality images hard to distinguish from real photos
Anime Generation
High-quality image generation
with complex structures
Anime Generation with DeNA AI
Our
Solution
Challenge
Back-
ground
Structure-Aware Generative Learning
Successful generation of diverse characters and animations
In 2018, AI generates high-quality images hard to distinguish from real photos
Anime Generation
High-quality image generation
with complex structures
Anime Generation with DeNA AI
Our
Solution
Challenge
Back-
ground
Structure-Aware Generative Learning
Successful generation of diverse characters and animations
Anime Inbetweening
Interpolation between frames
with large structural movement
In 2018, AI generates high-quality images hard to distinguish from real photos
Anime Generation
High-quality image generation
with complex structures
Progressive Structure-conditional GANs
(PSGAN)
Anime Generation with DeNA AI
Our
Solution
Challenge
Back-
ground
Structure-Aware Generative Learning
Successful generation of diverse characters and animations
Structure-consistent Prediction GANs
(SPGAN)
Progressive Structure-conditional GANs
(PSGAN)Structure-Aware Generative Learning
Anime Inbetweening
Interpolation between frames
with large structural movement
Anime Inbetweening with SPGAN
Anime Generation with PSGAN
AGENDA
Recent Progress on Image Generation and Issues
Conclusion
- Anime Generation with AI -
Overview
Our Approaches and Contributions
Other AI Solutions for Anime Production Issues
High-resolution and high-quality image generation with GANs
ProgressiveGAN (Karras et al., ICLR 2018) BigGAN (Brock et al., ICLR 2019)
Applications for Anime Production
have been limited to some specific cases, such as
- Generation for specific body parts (e.g. Face)
- Colorization (which does not treat structural generation)
AI-generated images have become higher resolution and quality
and are harder to distinguish from real photos
However, full-body image generation with complex structures has been a challenge
In 2018, AI generates high-quality images hard to distinguish from real photos
Anime Generation
High-quality image generation
with complex structures
Progressive Structure-conditional GANs
(PSGAN)
Anime Generation with DeNA AI
Our
Solution
Challenge
Back-
ground
Structure-Aware Generative Learning
Successful generation of diverse characters and animations
Structure-consistent Prediction GANs
(SPGAN)
Progressive Structure-conditional GANs
(PSGAN)Structure-Aware Generative Learning
Anime Inbetweening
Interpolation between frames
with large structural movement
Proposed method:
Progressive Structure-conditional GANs
(PSGAN)
Structure-Aware Generative Learning
Full-body High-resolution Anime Generation with Progressive Structure-conditional Generative Adversarial Networks
Koichi Hamada, Kentaro Tachibana, Tianqi Li, Hiroto Honda, and Yusuke Uchida. In ECCV Workshop 2018.
Anime Generation: Progressive Structure-conditional GANs (PSGAN) (Hamada+, ECCVW 2018)
Image generation of full-body and high-resolution characters
which has been a challenge due to its complex structure
Generated anime characters (1024x1024)
https://youtu.be/bIi5gSITK0E
Generation of brand new characters
Add animation to the new character by imposing a pose sequence
https://youtu.be/0LQlfkvQ3Ok
Full-body High-resolution Anime Generation with Progressive Structure-conditional Generative Adversarial Networks
Koichi Hamada, Kentaro Tachibana, Tianqi Li, Hiroto Honda, and Yusuke Uchida. In ECCV Workshop 2018.
Image generation of full-body and high-resolution characters
which has been a challenge due to its complex structure
Diverse characters and anime generation
Anime Generation: Progressive Structure-conditional GANs (PSGAN) (Hamada+, ECCVW 2018)
Generated anime characters (1024x1024)
https://youtu.be/bIi5gSITK0E
Generation of brand new characters
Add animation to the new character by imposing a pose sequence
https://youtu.be/0LQlfkvQ3Ok
Full-body High-resolution Anime Generation with Progressive Structure-conditional Generative Adversarial Networks
Koichi Hamada, Kentaro Tachibana, Tianqi Li, Hiroto Honda, and Yusuke Uchida. In ECCV Workshop 2018.
Proposed method: Progressive Structure-conditional GANs (PSGAN)
Learn to generate structure and image simultaneously
Stabilize generative learning of complex structures
by progressive network growth
4x4
4x4
1024x1024
4x4
4x4
Latent
Real Condition
1024x1024 1024x1024
Generated
1024x1024
512x512
512x512
1024x1024
Proposed method: Progressive Structure-conditional GANs (PSGAN)
4x4
4x4
4x4
4x4
Latent
Real Condition
4x4 4x44x4
Generated
Structure and image generation at low resolution for high-level context
Proposed method: Progressive Structure-conditional GANs (PSGAN)
4x4
4x4
8x8
4x4
8x8
4x4
Latent
Real Condition
8x8 8x88x8
Generated
Structure and image generation at low resolution for high-level context
Increase resolution in a step-by-step manner
to progressively learn to generate the detail structures
Proposed method: Progressive Structure-conditional GANs (PSGAN)
Structure and image generation at low resolution for high-level context
Increase resolution in a step-by-step manner
to progressively learn to generate the detail structures
4x4
4x4
1024x1024
4x4
4x4
Latent
Real Condition
1024x1024 1024x1024
Generated
1024x1024
512x512
512x512
1024x1024
Avatar Anime Dataset
A novel dataset containing diverse character images and 2D poses
Avatar Anime Dataset
A novel dataset containing diverse character images and 2D poses
Built by Unity 3D Avatar models and motions
Avatar Anime Dataset
Avatar Play
A novel dataset containing diverse character images and 2D poses
Built by Unity 3D Avatar models and motions
Developed utilizing 100 thousand 3D Avatar assets on the Mobage service
Generated Images: Progressive Structure-conditional GANs (PSGAN)
Image generation of full-body and high-resolution characters
which has been a challenge due to its complex structure
Diverse characters and anime generation
Generated anime characters (1024x1024)
https://youtu.be/bIi5gSITK0E
Generation of brand new characters
Add animation to the new character by imposing a pose sequence
https://youtu.be/0LQlfkvQ3Ok
Generated Images: Progressive Structure-conditional GANs (PSGAN)
https://youtu.be/bIi5gSITK0EFull-body anime generation at 1024x1024 with Progressive Structure-conditional GANs
Generated results of brand new characters
Generated Anime
(1024x1024)
Generated Images: Progressive Structure-conditional GANs (PSGAN)
https://youtu.be/0LQlfkvQ3OkAdding action to full-body anime characters with Progressive Structure-conditional GANs
Add animation to the new character by imposing a pose sequence
Generated Anime
(1024x1024)
Generated Images: Progressive Structure-conditional GANs (PSGAN)
(ICLR’18)
Structure Consistency: PSGAN’s images are more structure-consistent
Generated Images: Progressive Structure-conditional GANs (PSGAN)
(ICLR’18)
(NIPS’17) (NIPS’17)
Structure Consistency: PSGAN’s images are more structure-consistent
Image Quality on Pose Conditions: more detailed and high-quality
Generated Images: Progressive Structure-conditional GANs (PSGAN)
Generated Images
Application for realistic images:
Generation of new clothes with indicated pose
In 2018, AI generates high-quality images hard to distinguish from real photos
Anime Generation
High-quality image generation
with complex structures
Progressive Structure-conditional GANs
(PSGAN)
Anime Generation with DeNA AI
Our
Solution
Challenge
Back-
ground
Structure-Aware Generative Learning
Successful generation of diverse characters and animations
Structure-consistent Prediction GANs
(SPGAN)
Progressive Structure-conditional GANs
(PSGAN)Structure-Aware Generative Learning
Anime Inbetweening
Interpolation between frames
with large structural movement
In 2018, AI generates high-quality images hard to distinguish from real photos
Anime Generation
High-quality image generation
with complex structures
Progressive Structure-conditional GANs
(PSGAN)
Our
Solution
Challenge
Back-
ground
Structure-Aware Generative Learning
Successful generation of diverse characters and animations
Structure-consistent Prediction GANs
(SPGAN)
Progressive Structure-conditional GANs
(PSGAN)Structure-Aware Generative Learning
Anime Inbetweening
Interpolation between frames
with large structural movement
Anime Generation with DeNA AI
Anime Inbetweening with SPGAN
Anime Generation with PSGAN
AGENDA
Recent Progress on Image Generation and Issues
Conclusion
- Anime Generation with AI -
Overview
Our Approaches and Contributions
Other AI Solutions for Anime Production Issues
Current
Situation
Anime Inbetweening
Problems faced in Anime Production
Animator Web Report (in Japanese) (http://animatorweb.jp/)
• Limited time
• Limited budget
• Limited human resources
• Quality demands
Anime Inbetweening
Problems faced in Anime Production
Animator Web Report (in Japanese) (http://animatorweb.jp/)
Anime inbetweening
by animators
Anime Inbetweening
Animator Web Report (in Japanese) (http://animatorweb.jp/)
Anime Inbetweening
*
Anime inbetweening
by animators
original 1 original 2
*SSS STL WAO 2017 “Zunda Horizon”
Animator Web Report (in Japanese) (http://animatorweb.jp/)
Anime Inbetweening
original 1 original 2inbetweened
frames
*
Anime inbetweening
by animators
*SSS STL WAO 2017 “Zunda Horizon”
Animator Web Report (in Japanese) (http://animatorweb.jp/)
Anime Inbetweening
• Animators have to draw 3500-4000 inbetweens per one 30-
min anime episode
*
Anime inbetweening
by animators
original 1 original 2inbetweened
frames
*SSS STL WAO 2017 “Zunda Horizon”
Animator Web Report (in Japanese) (http://animatorweb.jp/)
Anime Inbetweening
• Animators have to draw 3500-4000 inbetweens per one 30-
min anime episode
• So much effort - hours to draw one inbetween
*
Anime inbetweening
by animators
original 1 original 2inbetweened
frames
*SSS STL WAO 2017 “Zunda Horizon”
Animator Web Report (in Japanese) (http://animatorweb.jp/)
Anime Inbetweening
*
• Animators have to draw 3500-4000 inbetweens per one 30-
min anime episode
• So much effort - hours to draw one inbetween
original 1 original 2inbetweened
frames
*SSS STL WAO 2017 “Zunda Horizon”
Animator Web Report (in Japanese) (http://animatorweb.jp/)
Anime inbetweening
by animators
Task definition
Anime Inbetweening
)3 Frame Interpolation 3 Frame
Automating anime inbetweening
Anime Inbetweening
)3 Frame Interpolation 3 Frame
Automating anime inbetweening
Anime Inbetweening
Automating anime inbetweening
AI
Automating anime inbetweening
Multi Frame Interpolation
Anime Inbetweening
AI
Related works
State-of-the-art frame interpolation method
Frame Interpolation
State-of-the-art frame interpolation method
Frame Interpolation
Super SloMo (Jiang+, CVPR’18)
Super SloMo: High Quality Estimation of Multiple Intermediate Frames for Video Interpolation.
Huaizu Jiang, Deqing Sun, Varun Jampani, Ming-Hsuan Yang, Erik Learned-Miller, Jan Kautz. In CVPR 2018.
State-of-the-art frame interpolation method
Frame Interpolation
Super SloMo (Jiang+, CVPR’18)
• Infer the intermediate frame from the input frame sequences at 30/60FPS
-> generate 240/480FPS (x8) video
Super SloMo: High Quality Estimation of Multiple Intermediate Frames for Video Interpolation.
Huaizu Jiang, Deqing Sun, Varun Jampani, Ming-Hsuan Yang, Erik Learned-Miller, Jan Kautz. In CVPR 2018.
https://youtu.be/MjViy6kyiqs
Research at NVIDIA: Transforming Standard Video Into Slow Motion with AI
State-of-the-art frame interpolation method
Frame Interpolation
Deep Voxel Flow (Liu+, ICCV’17)
Video Frame Synthesis using Deep Voxel Flow.
Ziwei Liu, Raymond A. Yeh, Xiaoou Tang, Yiming Liu, Aseem Agarwala. In ICCV 2017.
State-of-the-art frame interpolation method
Frame Interpolation
Deep Voxel Flow (Liu+, ICCV’17)
• Generate a 60fps video out of a 30FPS video
Video Frame Synthesis using Deep Voxel Flow.
Ziwei Liu, Raymond A. Yeh, Xiaoou Tang, Yiming Liu, Aseem Agarwala. In ICCV 2017.
https://youtu.be/qNXPI01WlBU?t=30s
Video Frame Synthesis using Deep Voxel Flow
State-of-the-art frame interpolation method
Frame Interpolation
Super SloMo (Jiang+, CVPR’18)
• Calculate Optical Flow-> synthesize intermediate frame-> refine
• Generate a 240/480FPS video out of a 30/60FPS video
Deep Voxel Flow (Liu+, ICCV’17)
• Calculate Optical Flow-> synthesize intermediate frame
• Competitive performance as Super SloMo
Super SloMo(Adobe)
Super SloMo
Deep Voxel Flow
Video Frame Synthesis using Deep Voxel Flow. Ziwei Liu, Raymond A. Yeh, Xiaoou Tang, Yiming Liu, Aseem Agarwala. In ICCV 2017.
Super SloMo: High Quality Estimation of Multiple Intermediate Frames for Video Interpolation. Huaizu Jiang, Deqing Sun, Varun
Jampani, Ming-Hsuan Yang, Erik Learned-Miller, Jan Kautz. In CVPR 2018.
Calculate Optical flow and Frame interpolation using Neural Networks
Frame Interpolation
Optical Flow
Vector map representing displacement (movement) of points
between two consecutive frames
High intensity = Large displacement
Issues of
the frame interpolation methods
Frame Interpolation does not work for anime inbetweening
Issue : Anime Inbetweening
Frame interpolation for frames with large structural displacement is key.
n Existing methods:
High-FPS input (30 60 → 240 480)
n Anime Inbetweening:
Low-FPS input (3 7 → 12 30)
*
*SSS STL WAO 2017 “Zunda Horizon”
Frame Interpolation does not work for anime inbetweening
Issue : Anime Inbetweening
n Existing methods:
Photo real
n Anime Inbetweening:
Illustration
*
Video Optical-flow
Illustration style is monotone in color, low textured -> Difficult to calculate Optical Flow.
*SSS STL WAO 2017 “Zunda Horizon”
Frame Interpolation does not work for anime inbetweening
Issue : Anime Inbetweening
Super SloMo
Deep Voxel Flow
…
Anime Inbetweening
Photo real Illustration
high-fps input
low-fps input
Proposed method:
Structure-consistent Prediction GANs
(SPGAN)
Structure-Aware Generative Learning
Challenges toward Anime Generation with Deep Generative Models
Koichi Hamada and Tianqi Li. In DeNA TechCon 2019.
A multi-task training using structural information and optical flow
Proposed method: Structure-consistent Prediction GANs (SPGAN)
n Input frames:
Multi-task
training
- Pose Keypoints:
n Optical Flow:
n Structure Information:
- Body-part masks:
Proposed method: Structure-consistent Prediction GANs (SPGAN)- pipeline
Structure Information
G
I0 I4
D
Optical Flow
I1, I2, I3
(Generated)
Ground Truth
MSE
MSE
Ground TruthStructure Information
(Generated)
A multi-task training using structural information and optical flow
Proposed method: Structure-consistent Prediction GANs (SPGAN)- Discriminator
Improve generation quality using two Discriminators
Proposed method: Structure-consistent Prediction GANs (SPGAN)- Discriminator
Conv-BN-ReLU
Conv-BN-ReLU
Conv-BN-ReLU
Conv-BN-ReLU
Local Discriminator
“Real” or “Fake”
Local Patch
(16×16pix)
Improve quality of details and time consistency
by Local Discriminator and Temporal Discriminator
Proposed method: Structure-consistent Prediction GANs (SPGAN)- Discriminator
Conv-BN-ReLU
Conv-BN-ReLU
Generated
Image Sequence
Conv-BN-ReLU
Conv-BN-ReLU
Conv-BN-ReLU
Conv-BN-ReLU
Conv-BN-ReLU
Conv-BN-ReLU
Conv-BN-ReLU
FC
Local Discriminator
Temporal Discriminator
“Real” or “Fake”
Local Patch
(16×16pix)
Image Sequence
“Real” or “Fake”
Improve quality of details and time consistency
by Local Discriminator and Temporal Discriminator
Experiment Settings
Experiment settings
Extract five consecutive frames from a video and
infer intermediate 3 frames using only the first and the last frames
Video
Experiment settings
Extract five consecutive frames from a video and
infer intermediate 3 frames using only the first and the last frames
image0 image1 image2 image3 image4Video
Experiment settings
Experiments using different frame steps
(different fps and structural displacement settings)
⁃ step size = 4 (7FPS -> 30FPS): 001.png, 005.png, 009.png, 013.png, 017.png
⁃ step size = 1 (30FPS -> 120FPS): 001.png, 002.png, 003.png, 004.png, 005.png
Experiment settings
⁃ step size = 4 (7FPS -> 30FPS): 001.png, 005.png, 009.png, 013.png, 017.png
⁃ step size = 1 (30FPS -> 120FPS): 001.png, 002.png, 003.png, 004.png, 005.png
Experiments using different frame steps
(different fps and structural displacement settings)
Experiment Results
Generated Results: Structure-consistent Prediction GANs (SPGAN)
Proposed method can interpolate the frames having large displacement
with good structural and time consistency
interpolation of frames
with small movement
SOTA model
Deep Voxel FlowInput
SPGAN
(Ours)
interpolation of frames
with large movement
Experimental Results: “Anime Frame Generation with Structure-consistent Prediction GANs” https://youtu.be/vXVr64BbXHY
https://youtu.be/X9j1fwexK2c?t=139Video:
Generated Results: Structure-consistent Prediction GANs (SPGAN)
step size = 1 step size = 4 step size = 7 step size = 10
Input
SPGAN
(Ours)
SoTA
Deep Voxel Flow
(ICCV’17)
Proposed method can interpolate the frames having large displacement
with good structural and time consistency
Small Structural displacement Large
Experimental Results: “Anime Frame Generation with Structure-consistent Prediction GANs” https://youtu.be/vXVr64BbXHY
https://youtu.be/X9j1fwexK2c?t=150Video:
Quantitative Evaluations: Structure-consistent Prediction GANs(SPGAN)
Deep Voxel Flow Ours
Average PSNR/SSIM on test dataset (step size=4)
PSNR SSIM
Deep Voxel Flow 23.32 0.9294
SPGAN(Ours) 24.27 0.9407
SPGAN (Ours)
Proposed method can interpolate the frames having large displacement
with good structural and time consistency
Anime Inbetweening with SPGAN
Anime Generation with PSGAN
AGENDA
Recent Progress on Image Generation and Issues
Conclusion
- Anime Generation with AI -
Overview
Our Approaches and Contributions
Other AI Solutions for Anime Production Issues
Issues in anime production
Today we will discuss the following five points
Process Issues
Overall process
Handling 4K/60fps (Making large key animation default, and increasing number of
inbetween frames)
Increased difficulty of managing processes & progress due to more complex
processes (2D, 3D, etc.), and separation of animation processes
Create layout (LO) Insufficient key animation pipeline
Create key animation frames (first) Insufficient key animation pipeline
Create key animation frames (second) Insufficient key animation pipeline
Animation supervising (characters)
Greater burden on animation supervising for characters due to more complex
character design
Animation supervising (action) Insufficient key animation pipeline
Create inbetweens Reduced pipeline & higher costs from overseas production companies
Finishing Reduced pipeline & higher costs from overseas production companies
In-between check
Demands to shorten check time in response to lengthened lead time for animation
(reduced post production time)
Background art Background / art delivery timing tending to be delayed, with more shoots
3D Lack of 3D animators and increased investment in education for training
Issues
DeNA AI: Overall process/ Animation (Inbetweens)
Input Frames AI Generated Frames
(x16 Generation)
x16 high-quality anime inbetweening
This makes creating 4K/60FPS animation easier
AI Generated Anime Inbetweening on Zunda Horizon* Test Data**
Our Generated Results:
https://youtu.be/X9j1fwexK2c?t=4AI Generated Results for Anime Inbetweening on “Zunda Horizon*” Test Data**:
**Trained using DeNA Dataset which does not include “Zunda Horizon” data*SSS STL WAO 2017 “Zunda Horizon”
Character drawn in new pose by designating style and drawing 2D stick figure
Changing the 2D stick figure makes the character move in accordance with 3D structure
This makes creating key animation easier
Character designation
Structuredesignation
(2Dposeinformation)
Generated examples
DeNA AI: Key Animation Frame/ Animation (Inbetweens)
https://youtu.be/X9j1fwexK2c?t=104Our Contribution:
Character drawn in new pose by designating style and drawing 2D stick figure
Changing the 2D stick figure makes the character move in accordance with 3D structure
This makes creating key animation easier
DeNA AI: Key Animation Frame/ Animation (Inbetweens)
Designate 2D pose series to animate the new characterNew character generation
https://youtu.be/bIi5gSITK0E https://youtu.be/0LQlfkvQ3Ok
https://youtu.be/Gz90H1M7_u4?t=50Video:https://youtu.be/X9j1fwexK2c?t=104Our Contribution:
Animation generation with a few images
Animation generated by designating roughs
This makes creating key animation & inbetweens easier
Image
(1 frame)
Rough designation
(structure designation)
Image
(1 frame)
Generated
result
Rough designation
(structure designation)
Generated
result
DeNA AI: Key Animation Frame/ Animation (Inbetweens)
https://youtu.be/X9j1fwexK2c?t=166Our Contribution:
Image
(1 frame)
Rough designation
(structure designation)
Image
(1 frame)
Generated
result
Rough designation
(structure designation)
Generated
result
Animation generation with a few images
Animation generated by designating roughs
This makes creating key animation & inbetweens easier
DeNA AI: Key Animation Frame/ Animation (Inbetweens)
https://youtu.be/X9j1fwexK2c?t=166Our Contribution: https://youtu.be/Gz90H1M7_u4?t=70Video:
Automated coloring reflecting color sample and line details
This makes finishing easier
Colorized example
(1 frame)
Generated resultRoughLines
https://youtu.be/X9j1fwexK2c?t=191Our Contribution: https://youtu.be/Gz90H1M7_u4?t=80Video:
DeNA AI: Finishing (Colorization)
Designate layout from art designation image and generate background art
with detailed textures from each structural element
Background automatically generated by drawing layout
Can allocate more time to drawing to raise background quality
Art designation image (1 frame) Generated resultLayout
https://youtu.be/X9j1fwexK2c?t=183Our Contribution:
DeNA AI: Background Art
Designate layout from art designation image and generate background art
with detailed textures from each structural element
Background automatically generated by drawing layout
Can allocate more time to drawing to raise background quality
Image (1 frame)
SFGAN
(Ours)Layout
SoTA model
SPADE (CVPR’19)
Generated Result
https://youtu.be/X9j1fwexK2c?t=183Our Contribution:
DeNA AI: Background Art
Anime Inbetweening with SPGAN
Anime Generation with PSGAN
AGENDA
Recent Progress on Image Generation and Issues
Conclusion
- Anime Generation with AI -
Overview
Our Approaches and Contributions
Other AI Solutions for Anime Production Issues
Input Frames AI Generated Frames
(x16 Generation)
AI Anime Inbetweening for a wide variety of objects
**Trained using DeNA Dataset which does not include “Zunda Horizon” data*SSS STL WAO 2017 “Zunda Horizon”
Generated Anime: https://youtu.be/X9j1fwexK2c?t=4
AI Generated Anime Inbetweening on Zunda Horizon* Test Data**
AI Generated Anime Inbetweening on Zunda Horizon* Test Data**
Comparison with human animators
**Trained using DeNA Dataset which does not include “Zunda Horizon” data*SSS STL WAO 2017 “Zunda Horizon”
AI Generated Frames
(x4 Generation)
Actual Frames
drawn by Human Animators
(x4 Generation)
Input Frames
Generated Anime: https://youtu.be/X9j1fwexK2c?t=80
High-resolution and high-quality image generation with GANs
ProgressiveGAN (Karras et al., ICLR 2018) BigGAN (Brock et al., ICLR 2019)
AI-generated images have become higher resolution and quality
and are harder to distinguish from real photos
However, full-body image generation with complex structures has been a challenge
High-resolution and high-quality image generation with GANs
ProgressiveGAN (Karras et al., ICLR 2018) BigGAN (Brock et al., ICLR 2019)
Applications for Anime Production
Limited to some specific cases, such as
- Generation for specific body parts (e.g. Face)
- Colorization (which does not treat structural generation)
AI-generated images have become higher resolution and quality
and are harder to distinguish from real photos
However, full-body image generation with complex structures has been a challenge
Anime Generation with DeNA AI
Generated Anime
4x4
4x4
1024x1024
4x4
4x4
Latent
Real Condition
1024x1024 1024x1024
1024x1024
512x512
512x512
1024x1024
Add animation to the new character
by imposing a pose sequence
Generation of brand new characters
Progressive Structure-conditional GANs (PSGAN)
Generated
Full-body High-resolution Anime Generation with Progressive Structure-conditional Generative Adversarial Networks.
Koichi Hamada, Kentaro Tachibana, Tianqi Li, Hiroto Honda, and Yusuke Uchida. In ECCV Workshop 2018.
Successful image generation of full-body and high-resolution characters
Diverse characters and anime generation
https://youtu.be/X9j1fwexK2c?t=104Generated Anime:
Successful video interpolation between frames with large structural movement
Anime inbetweening
Anime Generation with DeNA AI
Input SPGAN
(Ours)
SOTA model
Deep Voxel Flow
Structure-consistent Prediction GANs (SPGAN)
Deep Voxel Flow
(ICCV’17)
Deep Voxel Flow
(ICCV'17)
PSNR
SSIM
Structured displacement
SPGAN
(Ours)
SPGAN
(Ours)
Structural displacementStructural displacement
Challenges toward Anime Generation with Deep Generative Models.
Koichi Hamada and Tianqi Li. In DeNA TechCon 2019. https://youtu.be/X9j1fwexK2c?t=132Generated Anime:
Successful image generation with detailed textures for each structural element
Anime generation with a few images
Anime Generation with DeNA AI
Structural Feature-embedding GANs (SFGAN)
Rough designation
(Structure designation)
Generated
result
Rough designation
(Structure designation)
Generated
result
Image
(1 frame)
Image
(1 frame)
https://youtu.be/X9j1fwexK2c?t=166Generated Anime:
Successful landscape generation with designated detailed texture for each part
Background art generation
Anime Generation with DeNA AI
Structural Feature-embedding GANs (SFGAN)
Image (1 frame)
SFGAN
(Ours)Layout
SoTA model
SPADE (CVPR’19)
Generated Result
Successful colorization that exactly reflects color example and line details
Exact colorization based on colorized example
Anime Generation with DeNA AI
Colorized example (1 frame) Colorized resultLines Rough
Structural Feature-embedding GANs (SFGAN)
https://youtu.be/X9j1fwexK2c?t=191Generated Anime:
In 2018, AI generates high-quality images hard to distinguish from real photos
Anime Generation
High-quality image generation
with complex structures
Progressive Structure-conditional GANs
(PSGAN)
Anime Generation with DeNA AI
Our
Solution
Challenge
Back-
ground
Structure-Aware Generative Learning
Successful generation of diverse characters and animations
Structure-consistent Prediction GANs
(SPGAN)
Progressive Structure-conditional GANs
(PSGAN)Structure-Aware Generative Learning
Anime Inbetweening
Interpolation between frames
with large structural movement
There are great possibilities for AI-generated animation
At DeNA, we challenge ourselves to provide
new value in anime generation
We would be happy if we could work together with you
to create a better future for animation production
ai@dena.com
Please contact us
@hamadakoichi
Koichi Hamada
Anime Generation with DeNA AI

More Related Content

What's hot

研究室内PRML勉強会 8章1節
研究室内PRML勉強会 8章1節研究室内PRML勉強会 8章1節
研究室内PRML勉強会 8章1節
Koji Matsuda
 

What's hot (20)

自己教師学習(Self-Supervised Learning)
自己教師学習(Self-Supervised Learning)自己教師学習(Self-Supervised Learning)
自己教師学習(Self-Supervised Learning)
 
Transformerを多層にする際の勾配消失問題と解決法について
Transformerを多層にする際の勾配消失問題と解決法についてTransformerを多層にする際の勾配消失問題と解決法について
Transformerを多層にする際の勾配消失問題と解決法について
 
【DL輪読会】Poisoning Language Models During Instruction Tuning Instruction Tuning...
【DL輪読会】Poisoning Language Models During Instruction Tuning Instruction Tuning...【DL輪読会】Poisoning Language Models During Instruction Tuning Instruction Tuning...
【DL輪読会】Poisoning Language Models During Instruction Tuning Instruction Tuning...
 
サイバーエージェントにおけるMLOpsに関する取り組み at PyDataTokyo 23
サイバーエージェントにおけるMLOpsに関する取り組み at PyDataTokyo 23サイバーエージェントにおけるMLOpsに関する取り組み at PyDataTokyo 23
サイバーエージェントにおけるMLOpsに関する取り組み at PyDataTokyo 23
 
You Only Look One-level Featureの解説と見せかけた物体検出のよもやま話
You Only Look One-level Featureの解説と見せかけた物体検出のよもやま話You Only Look One-level Featureの解説と見せかけた物体検出のよもやま話
You Only Look One-level Featureの解説と見せかけた物体検出のよもやま話
 
東北大学 先端技術の基礎と実践_深層学習による画像認識とデータの話_菊池悠太
東北大学 先端技術の基礎と実践_深層学習による画像認識とデータの話_菊池悠太東北大学 先端技術の基礎と実践_深層学習による画像認識とデータの話_菊池悠太
東北大学 先端技術の基礎と実践_深層学習による画像認識とデータの話_菊池悠太
 
MLflowで学ぶMLOpsことはじめ
MLflowで学ぶMLOpsことはじめMLflowで学ぶMLOpsことはじめ
MLflowで学ぶMLOpsことはじめ
 
[DL輪読会]VoxelPose: Towards Multi-Camera 3D Human Pose Estimation in Wild Envir...
[DL輪読会]VoxelPose: Towards Multi-Camera 3D Human Pose Estimation in Wild Envir...[DL輪読会]VoxelPose: Towards Multi-Camera 3D Human Pose Estimation in Wild Envir...
[DL輪読会]VoxelPose: Towards Multi-Camera 3D Human Pose Estimation in Wild Envir...
 
論文紹介:Temporal Action Segmentation: An Analysis of Modern Techniques
論文紹介:Temporal Action Segmentation: An Analysis of Modern Techniques論文紹介:Temporal Action Segmentation: An Analysis of Modern Techniques
論文紹介:Temporal Action Segmentation: An Analysis of Modern Techniques
 
GAN(と強化学習との関係)
GAN(と強化学習との関係)GAN(と強化学習との関係)
GAN(と強化学習との関係)
 
AI勉強会用スライド
AI勉強会用スライドAI勉強会用スライド
AI勉強会用スライド
 
全力解説!Transformer
全力解説!Transformer全力解説!Transformer
全力解説!Transformer
 
Wandb Monthly Meetup August 2023.pdf
Wandb Monthly Meetup August 2023.pdfWandb Monthly Meetup August 2023.pdf
Wandb Monthly Meetup August 2023.pdf
 
研究室内PRML勉強会 8章1節
研究室内PRML勉強会 8章1節研究室内PRML勉強会 8章1節
研究室内PRML勉強会 8章1節
 
【DL輪読会】Perceiver io a general architecture for structured inputs & outputs
【DL輪読会】Perceiver io  a general architecture for structured inputs & outputs 【DL輪読会】Perceiver io  a general architecture for structured inputs & outputs
【DL輪読会】Perceiver io a general architecture for structured inputs & outputs
 
[DL輪読会]相互情報量最大化による表現学習
[DL輪読会]相互情報量最大化による表現学習[DL輪読会]相互情報量最大化による表現学習
[DL輪読会]相互情報量最大化による表現学習
 
MLOpsはバズワード
MLOpsはバズワードMLOpsはバズワード
MLOpsはバズワード
 
文献紹介:TSM: Temporal Shift Module for Efficient Video Understanding
文献紹介:TSM: Temporal Shift Module for Efficient Video Understanding文献紹介:TSM: Temporal Shift Module for Efficient Video Understanding
文献紹介:TSM: Temporal Shift Module for Efficient Video Understanding
 
【DL輪読会】Segment Anything
【DL輪読会】Segment Anything【DL輪読会】Segment Anything
【DL輪読会】Segment Anything
 
【論文紹介】U-GAT-IT
【論文紹介】U-GAT-IT【論文紹介】U-GAT-IT
【論文紹介】U-GAT-IT
 

Similar to Anime Generation with AI

Similar to Anime Generation with AI (20)

Generative adversarial network and its applications to speech signal and natu...
Generative adversarial network and its applications to speech signal and natu...Generative adversarial network and its applications to speech signal and natu...
Generative adversarial network and its applications to speech signal and natu...
 
Generative Adversarial Network and its Applications to Speech Processing an...
Generative Adversarial Network and its Applications to Speech Processing an...Generative Adversarial Network and its Applications to Speech Processing an...
Generative Adversarial Network and its Applications to Speech Processing an...
 
David Helgason
David HelgasonDavid Helgason
David Helgason
 
Presentation 20110918 after effect
Presentation 20110918   after effectPresentation 20110918   after effect
Presentation 20110918 after effect
 
PremiumARTS Inc profile shortB_e_20171218
PremiumARTS Inc profile shortB_e_20171218PremiumARTS Inc profile shortB_e_20171218
PremiumARTS Inc profile shortB_e_20171218
 
Google Dev Group Yangon (2020) AI Talk (Creative AI in Action)
Google Dev Group Yangon (2020)  AI Talk (Creative AI in Action)Google Dev Group Yangon (2020)  AI Talk (Creative AI in Action)
Google Dev Group Yangon (2020) AI Talk (Creative AI in Action)
 
Sprite js vs craftyjs
Sprite js vs craftyjsSprite js vs craftyjs
Sprite js vs craftyjs
 
Presentation 20110918 split
Presentation 20110918   splitPresentation 20110918   split
Presentation 20110918 split
 
Resume subbu addanki
Resume subbu addankiResume subbu addanki
Resume subbu addanki
 
Alexey Savchenko, Unreal Engine
Alexey Savchenko, Unreal EngineAlexey Savchenko, Unreal Engine
Alexey Savchenko, Unreal Engine
 
IRJET- Transformation of Realistic Images and Videos into Cartoon Images and ...
IRJET- Transformation of Realistic Images and Videos into Cartoon Images and ...IRJET- Transformation of Realistic Images and Videos into Cartoon Images and ...
IRJET- Transformation of Realistic Images and Videos into Cartoon Images and ...
 
Generative adversarial networks
Generative adversarial networksGenerative adversarial networks
Generative adversarial networks
 
Datt 2501 week 11
Datt 2501 week 11Datt 2501 week 11
Datt 2501 week 11
 
보다 유연한 이미지 변환을 하려면?
보다 유연한 이미지 변환을 하려면?보다 유연한 이미지 변환을 하려면?
보다 유연한 이미지 변환을 하려면?
 
Javascript Animation with Canvas - Gregory Starr 2015
Javascript Animation with Canvas - Gregory Starr 2015Javascript Animation with Canvas - Gregory Starr 2015
Javascript Animation with Canvas - Gregory Starr 2015
 
Discover the technology behind "The Heretic" – Unite Copenhagen 2019
Discover the technology behind "The Heretic" – Unite Copenhagen 2019Discover the technology behind "The Heretic" – Unite Copenhagen 2019
Discover the technology behind "The Heretic" – Unite Copenhagen 2019
 
Create your own avatar or integrate our engine into your metaverse
Create your own avatar or integrate our engine into your metaverseCreate your own avatar or integrate our engine into your metaverse
Create your own avatar or integrate our engine into your metaverse
 
Unity
UnityUnity
Unity
 
Applying AI in Games (GDC2019)
Applying AI in Games (GDC2019)Applying AI in Games (GDC2019)
Applying AI in Games (GDC2019)
 
[Pandora 22] ...Deliberately Unsupervised Playground - Milan Licina
[Pandora 22] ...Deliberately Unsupervised Playground - Milan Licina[Pandora 22] ...Deliberately Unsupervised Playground - Milan Licina
[Pandora 22] ...Deliberately Unsupervised Playground - Milan Licina
 

More from Koichi Hamada

Mahout JP - #TokyoWebmining 11th #MahoutJP
Mahout JP -  #TokyoWebmining 11th #MahoutJP Mahout JP -  #TokyoWebmining 11th #MahoutJP
Mahout JP - #TokyoWebmining 11th #MahoutJP
Koichi Hamada
 

More from Koichi Hamada (20)

Generative Adversarial Networks @ ICML 2019
Generative Adversarial Networks @ ICML 2019Generative Adversarial Networks @ ICML 2019
Generative Adversarial Networks @ ICML 2019
 
Generative Adversarial Networks (GANs) and Disentangled Representations @ N...
Generative Adversarial Networks (GANs) and Disentangled Representations @ N...Generative Adversarial Networks (GANs) and Disentangled Representations @ N...
Generative Adversarial Networks (GANs) and Disentangled Representations @ N...
 
Generative Adversarial Networks (GAN) @ NIPS2017
Generative Adversarial Networks (GAN) @ NIPS2017Generative Adversarial Networks (GAN) @ NIPS2017
Generative Adversarial Networks (GAN) @ NIPS2017
 
DeNAのAI活用したサービス開発
DeNAのAI活用したサービス開発DeNAのAI活用したサービス開発
DeNAのAI活用したサービス開発
 
対話返答生成における個性の追加反映
対話返答生成における個性の追加反映対話返答生成における個性の追加反映
対話返答生成における個性の追加反映
 
Generative Adversarial Networks (GAN) の学習方法進展・画像生成・教師なし画像変換
Generative Adversarial Networks (GAN) の学習方法進展・画像生成・教師なし画像変換Generative Adversarial Networks (GAN) の学習方法進展・画像生成・教師なし画像変換
Generative Adversarial Networks (GAN) の学習方法進展・画像生成・教師なし画像変換
 
NIPS 2016 Overview and Deep Learning Topics
NIPS 2016 Overview and Deep Learning Topics  NIPS 2016 Overview and Deep Learning Topics
NIPS 2016 Overview and Deep Learning Topics
 
DeNAの機械学習・深層学習活用した 体験提供の挑戦
DeNAの機械学習・深層学習活用した体験提供の挑戦DeNAの機械学習・深層学習活用した体験提供の挑戦
DeNAの機械学習・深層学習活用した 体験提供の挑戦
 
Laplacian Pyramid of Generative Adversarial Networks (LAPGAN) - NIPS2015読み会 #...
Laplacian Pyramid of Generative Adversarial Networks (LAPGAN) - NIPS2015読み会 #...Laplacian Pyramid of Generative Adversarial Networks (LAPGAN) - NIPS2015読み会 #...
Laplacian Pyramid of Generative Adversarial Networks (LAPGAN) - NIPS2015読み会 #...
 
DeNAの大規模データマイニング活用したサービス開発
DeNAの大規模データマイニング活用したサービス開発DeNAの大規模データマイニング活用したサービス開発
DeNAの大規模データマイニング活用したサービス開発
 
『MobageのAnalytics活用したサービス開発』 - データマイニングCROSS2014 #CROSS2014
『MobageのAnalytics活用したサービス開発』 - データマイニングCROSS2014 #CROSS2014『MobageのAnalytics活用したサービス開発』 - データマイニングCROSS2014 #CROSS2014
『MobageのAnalytics活用したサービス開発』 - データマイニングCROSS2014 #CROSS2014
 
『Mobageの大規模データマイニング活用と 意思決定』- #IBIS 2012 -ビジネスと機械学習の接点-
『Mobageの大規模データマイニング活用と 意思決定』- #IBIS 2012 -ビジネスと機械学習の接点- 『Mobageの大規模データマイニング活用と 意思決定』- #IBIS 2012 -ビジネスと機械学習の接点-
『Mobageの大規模データマイニング活用と 意思決定』- #IBIS 2012 -ビジネスと機械学習の接点-
 
複雑ネットワーク上の伝搬法則の数理
複雑ネットワーク上の伝搬法則の数理複雑ネットワーク上の伝搬法則の数理
複雑ネットワーク上の伝搬法則の数理
 
データマイニングCROSS 2012 Opening Talk - データマイニングの実サービス・ビジネス適用と展望
データマイニングCROSS 2012 Opening Talk - データマイニングの実サービス・ビジネス適用と展望 データマイニングCROSS 2012 Opening Talk - データマイニングの実サービス・ビジネス適用と展望
データマイニングCROSS 2012 Opening Talk - データマイニングの実サービス・ビジネス適用と展望
 
データマイニングCROSS 第2部-機械学習・大規模分散処理
データマイニングCROSS 第2部-機械学習・大規模分散処理データマイニングCROSS 第2部-機械学習・大規模分散処理
データマイニングCROSS 第2部-機械学習・大規模分散処理
 
Large Scale Data Mining of the Mobage Service - #PRMU 2011 #Mahout #Hadoop
Large Scale Data Mining of the Mobage Service - #PRMU 2011 #Mahout #HadoopLarge Scale Data Mining of the Mobage Service - #PRMU 2011 #Mahout #Hadoop
Large Scale Data Mining of the Mobage Service - #PRMU 2011 #Mahout #Hadoop
 
"Mahout Recommendation" - #TokyoWebmining 14th
"Mahout Recommendation" -  #TokyoWebmining 14th"Mahout Recommendation" -  #TokyoWebmining 14th
"Mahout Recommendation" - #TokyoWebmining 14th
 
Mahout JP - #TokyoWebmining 11th #MahoutJP
Mahout JP -  #TokyoWebmining 11th #MahoutJP Mahout JP -  #TokyoWebmining 11th #MahoutJP
Mahout JP - #TokyoWebmining 11th #MahoutJP
 
10回開催記念 「データマイニング+WEB ~データマイニング・機械学習活用による継続進化~」ー第10回データマイニング+WEB勉強会@東京ー #Toky...
10回開催記念 「データマイニング+WEB ~データマイニング・機械学習活用による継続進化~」ー第10回データマイニング+WEB勉強会@東京ー #Toky...10回開催記念 「データマイニング+WEB ~データマイニング・機械学習活用による継続進化~」ー第10回データマイニング+WEB勉強会@東京ー #Toky...
10回開催記念 「データマイニング+WEB ~データマイニング・機械学習活用による継続進化~」ー第10回データマイニング+WEB勉強会@東京ー #Toky...
 
『モバゲーの大規模データマイニング基盤におけるHadoop活用』-Hadoop Conference Japan 2011- #hcj2011
『モバゲーの大規模データマイニング基盤におけるHadoop活用』-Hadoop Conference Japan 2011- #hcj2011 『モバゲーの大規模データマイニング基盤におけるHadoop活用』-Hadoop Conference Japan 2011- #hcj2011
『モバゲーの大規模データマイニング基盤におけるHadoop活用』-Hadoop Conference Japan 2011- #hcj2011
 

Recently uploaded

Abortion pills in Jeddah | +966572737505 | Get Cytotec
Abortion pills in Jeddah | +966572737505 | Get CytotecAbortion pills in Jeddah | +966572737505 | Get Cytotec
Abortion pills in Jeddah | +966572737505 | Get Cytotec
Abortion pills in Riyadh +966572737505 get cytotec
 
Reconciling Conflicting Data Curation Actions: Transparency Through Argument...
Reconciling Conflicting Data Curation Actions:  Transparency Through Argument...Reconciling Conflicting Data Curation Actions:  Transparency Through Argument...
Reconciling Conflicting Data Curation Actions: Transparency Through Argument...
Bertram Ludäscher
 
如何办理英国诺森比亚大学毕业证(NU毕业证书)成绩单原件一模一样
如何办理英国诺森比亚大学毕业证(NU毕业证书)成绩单原件一模一样如何办理英国诺森比亚大学毕业证(NU毕业证书)成绩单原件一模一样
如何办理英国诺森比亚大学毕业证(NU毕业证书)成绩单原件一模一样
wsppdmt
 
Top profile Call Girls In Purnia [ 7014168258 ] Call Me For Genuine Models We...
Top profile Call Girls In Purnia [ 7014168258 ] Call Me For Genuine Models We...Top profile Call Girls In Purnia [ 7014168258 ] Call Me For Genuine Models We...
Top profile Call Girls In Purnia [ 7014168258 ] Call Me For Genuine Models We...
nirzagarg
 
Top profile Call Girls In Vadodara [ 7014168258 ] Call Me For Genuine Models ...
Top profile Call Girls In Vadodara [ 7014168258 ] Call Me For Genuine Models ...Top profile Call Girls In Vadodara [ 7014168258 ] Call Me For Genuine Models ...
Top profile Call Girls In Vadodara [ 7014168258 ] Call Me For Genuine Models ...
gajnagarg
 
+97470301568>>weed for sale in qatar ,weed for sale in dubai,weed for sale in...
+97470301568>>weed for sale in qatar ,weed for sale in dubai,weed for sale in...+97470301568>>weed for sale in qatar ,weed for sale in dubai,weed for sale in...
+97470301568>>weed for sale in qatar ,weed for sale in dubai,weed for sale in...
Health
 
In Riyadh ((+919101817206)) Cytotec kit @ Abortion Pills Saudi Arabia
In Riyadh ((+919101817206)) Cytotec kit @ Abortion Pills Saudi ArabiaIn Riyadh ((+919101817206)) Cytotec kit @ Abortion Pills Saudi Arabia
In Riyadh ((+919101817206)) Cytotec kit @ Abortion Pills Saudi Arabia
ahmedjiabur940
 
Computer science Sql cheat sheet.pdf.pdf
Computer science Sql cheat sheet.pdf.pdfComputer science Sql cheat sheet.pdf.pdf
Computer science Sql cheat sheet.pdf.pdf
SayantanBiswas37
 
Top profile Call Girls In Satna [ 7014168258 ] Call Me For Genuine Models We ...
Top profile Call Girls In Satna [ 7014168258 ] Call Me For Genuine Models We ...Top profile Call Girls In Satna [ 7014168258 ] Call Me For Genuine Models We ...
Top profile Call Girls In Satna [ 7014168258 ] Call Me For Genuine Models We ...
nirzagarg
 
Lecture_2_Deep_Learning_Overview-newone1
Lecture_2_Deep_Learning_Overview-newone1Lecture_2_Deep_Learning_Overview-newone1
Lecture_2_Deep_Learning_Overview-newone1
ranjankumarbehera14
 

Recently uploaded (20)

Abortion pills in Jeddah | +966572737505 | Get Cytotec
Abortion pills in Jeddah | +966572737505 | Get CytotecAbortion pills in Jeddah | +966572737505 | Get Cytotec
Abortion pills in Jeddah | +966572737505 | Get Cytotec
 
SAC 25 Final National, Regional & Local Angel Group Investing Insights 2024 0...
SAC 25 Final National, Regional & Local Angel Group Investing Insights 2024 0...SAC 25 Final National, Regional & Local Angel Group Investing Insights 2024 0...
SAC 25 Final National, Regional & Local Angel Group Investing Insights 2024 0...
 
5CL-ADBA,5cladba, Chinese supplier, safety is guaranteed
5CL-ADBA,5cladba, Chinese supplier, safety is guaranteed5CL-ADBA,5cladba, Chinese supplier, safety is guaranteed
5CL-ADBA,5cladba, Chinese supplier, safety is guaranteed
 
TrafficWave Generator Will Instantly drive targeted and engaging traffic back...
TrafficWave Generator Will Instantly drive targeted and engaging traffic back...TrafficWave Generator Will Instantly drive targeted and engaging traffic back...
TrafficWave Generator Will Instantly drive targeted and engaging traffic back...
 
Reconciling Conflicting Data Curation Actions: Transparency Through Argument...
Reconciling Conflicting Data Curation Actions:  Transparency Through Argument...Reconciling Conflicting Data Curation Actions:  Transparency Through Argument...
Reconciling Conflicting Data Curation Actions: Transparency Through Argument...
 
如何办理英国诺森比亚大学毕业证(NU毕业证书)成绩单原件一模一样
如何办理英国诺森比亚大学毕业证(NU毕业证书)成绩单原件一模一样如何办理英国诺森比亚大学毕业证(NU毕业证书)成绩单原件一模一样
如何办理英国诺森比亚大学毕业证(NU毕业证书)成绩单原件一模一样
 
Top profile Call Girls In Purnia [ 7014168258 ] Call Me For Genuine Models We...
Top profile Call Girls In Purnia [ 7014168258 ] Call Me For Genuine Models We...Top profile Call Girls In Purnia [ 7014168258 ] Call Me For Genuine Models We...
Top profile Call Girls In Purnia [ 7014168258 ] Call Me For Genuine Models We...
 
Top profile Call Girls In Vadodara [ 7014168258 ] Call Me For Genuine Models ...
Top profile Call Girls In Vadodara [ 7014168258 ] Call Me For Genuine Models ...Top profile Call Girls In Vadodara [ 7014168258 ] Call Me For Genuine Models ...
Top profile Call Girls In Vadodara [ 7014168258 ] Call Me For Genuine Models ...
 
+97470301568>>weed for sale in qatar ,weed for sale in dubai,weed for sale in...
+97470301568>>weed for sale in qatar ,weed for sale in dubai,weed for sale in...+97470301568>>weed for sale in qatar ,weed for sale in dubai,weed for sale in...
+97470301568>>weed for sale in qatar ,weed for sale in dubai,weed for sale in...
 
In Riyadh ((+919101817206)) Cytotec kit @ Abortion Pills Saudi Arabia
In Riyadh ((+919101817206)) Cytotec kit @ Abortion Pills Saudi ArabiaIn Riyadh ((+919101817206)) Cytotec kit @ Abortion Pills Saudi Arabia
In Riyadh ((+919101817206)) Cytotec kit @ Abortion Pills Saudi Arabia
 
20240412-SmartCityIndex-2024-Full-Report.pdf
20240412-SmartCityIndex-2024-Full-Report.pdf20240412-SmartCityIndex-2024-Full-Report.pdf
20240412-SmartCityIndex-2024-Full-Report.pdf
 
Computer science Sql cheat sheet.pdf.pdf
Computer science Sql cheat sheet.pdf.pdfComputer science Sql cheat sheet.pdf.pdf
Computer science Sql cheat sheet.pdf.pdf
 
Aspirational Block Program Block Syaldey District - Almora
Aspirational Block Program Block Syaldey District - AlmoraAspirational Block Program Block Syaldey District - Almora
Aspirational Block Program Block Syaldey District - Almora
 
Top profile Call Girls In Satna [ 7014168258 ] Call Me For Genuine Models We ...
Top profile Call Girls In Satna [ 7014168258 ] Call Me For Genuine Models We ...Top profile Call Girls In Satna [ 7014168258 ] Call Me For Genuine Models We ...
Top profile Call Girls In Satna [ 7014168258 ] Call Me For Genuine Models We ...
 
DATA SUMMIT 24 Building Real-Time Pipelines With FLaNK
DATA SUMMIT 24  Building Real-Time Pipelines With FLaNKDATA SUMMIT 24  Building Real-Time Pipelines With FLaNK
DATA SUMMIT 24 Building Real-Time Pipelines With FLaNK
 
Vadodara 💋 Call Girl 7737669865 Call Girls in Vadodara Escort service book now
Vadodara 💋 Call Girl 7737669865 Call Girls in Vadodara Escort service book nowVadodara 💋 Call Girl 7737669865 Call Girls in Vadodara Escort service book now
Vadodara 💋 Call Girl 7737669865 Call Girls in Vadodara Escort service book now
 
Lecture_2_Deep_Learning_Overview-newone1
Lecture_2_Deep_Learning_Overview-newone1Lecture_2_Deep_Learning_Overview-newone1
Lecture_2_Deep_Learning_Overview-newone1
 
Dubai Call Girls Peeing O525547819 Call Girls Dubai
Dubai Call Girls Peeing O525547819 Call Girls DubaiDubai Call Girls Peeing O525547819 Call Girls Dubai
Dubai Call Girls Peeing O525547819 Call Girls Dubai
 
Statistics notes ,it includes mean to index numbers
Statistics notes ,it includes mean to index numbersStatistics notes ,it includes mean to index numbers
Statistics notes ,it includes mean to index numbers
 
High Profile Call Girls Service in Jalore { 9332606886 } VVIP NISHA Call Girl...
High Profile Call Girls Service in Jalore { 9332606886 } VVIP NISHA Call Girl...High Profile Call Girls Service in Jalore { 9332606886 } VVIP NISHA Call Girl...
High Profile Call Girls Service in Jalore { 9332606886 } VVIP NISHA Call Girl...
 

Anime Generation with AI

  • 1. Anime Generation with AI Koichi Hamada AI Unit, DeNA Co., Ltd., Tokyo, Japan
  • 2. Anime Inbetweening with SPGAN Anime Generation with PSGAN AGENDA Recent Progress on Image Generation and Issues Conclusion - Anime Generation with AI - Overview Our Approaches and Contributions Other AI Solutions for Anime Production Issues
  • 3. Anime Inbetweening with SPGAN Anime Generation with PSGAN AGENDA Recent Progress on Image Generation and Issues Conclusion - Anime Generation with AI - Overview Our Approaches and Contributions Other AI Solutions for Anime Production Issues
  • 4. AI Generated Anime Inbetweening on Zunda Horizon* Test Data** Input Frames AI Generated Frames (x16 Generation) AI anime inbetweening for a wide variety of objects **Trained using DeNA Dataset which does not include “Zunda Horizon” data*SSS STL WAO 2017 “Zunda Horizon” Generated Anime: https://youtu.be/X9j1fwexK2c?t=4
  • 5. AI Generated Anime Inbetweening on Zunda Horizon* Test Data** AI Generated Frames (x4 Generation) Actual Frames drawn by Human Animators (x4 Generation) Input Frames Comparison with human animators **Trained using DeNA Dataset which does not include “Zunda Horizon” data*SSS STL WAO 2017 “Zunda Horizon” Generated Anime: https://youtu.be/X9j1fwexK2c?t=80
  • 6. Anime Generation with DeNA AI Generated Anime 4x4 4x4 1024x1024 4x4 4x4 Latent Real Condition 1024x1024 1024x1024 1024x1024 512x512 512x512 1024x1024 Add animation to the new character by imposing a pose sequence Generation of brand new characters Progressive Structure-conditional GANs (PSGAN) Generated Full-body High-resolution Anime Generation with Progressive Structure-conditional Generative Adversarial Networks. Koichi Hamada, Kentaro Tachibana, Tianqi Li, Hiroto Honda, and Yusuke Uchida. In ECCV Workshop 2018. Successful image generation of full-body and high-resolution characters Diverse characters and anime generation https://youtu.be/X9j1fwexK2c?t=104Generated Anime:
  • 7. Successful video interpolation between frames with large structural movement Anime inbetweening Anime Generation with DeNA AI Input SPGAN (Ours) SOTA model Deep Voxel Flow Structure-consistent Prediction GANs (SPGAN) Deep Voxel Flow (ICCV’17) Deep Voxel Flow (ICCV'17) PSNR SSIM Structured displacement SPGAN (Ours) SPGAN (Ours) Structural displacementStructural displacement Challenges toward Anime Generation with Deep Generative Models. Koichi Hamada and Tianqi Li. In DeNA TechCon 2019. https://youtu.be/X9j1fwexK2c?t=132Generated Anime:
  • 8. Successful image generation with detailed textures for each structural element Anime generation with a few images Anime Generation with DeNA AI Structural Feature-embedding GANs (SFGAN) Rough designation (Structure designation) Generated result Rough designation (Structure designation) Generated result Image (1 frame) Image (1 frame) https://youtu.be/X9j1fwexK2c?t=166Generated Anime:
  • 9. Successful landscape generation with designated detailed texture for each part Background art generation Anime Generation with DeNA AI Structural Feature-embedding GANs (SFGAN) Image (1 frame) SFGAN (Ours)Layout SoTA model SPADE (CVPR’19) Generated Result
  • 10. Successful colorization that exactly reflects color example and line details Exact colorization based on colorized example Anime Generation with DeNA AI Colorized example (1 frame) Colorized resultLines Rough Structural Feature-embedding GANs (SFGAN) https://youtu.be/X9j1fwexK2c?t=191Generated Anime:
  • 11. Structure-Aware Generative Learning A key solution for these challenges Anime Generation with DeNA AI We propose:
  • 12. In 2018, AI generates high-quality images hard to distinguish from real photos Anime Generation High-quality image generation with complex structures Progressive Structure-conditional GANs (PSGAN) Our Solution Challenge Back- ground Structure-Aware Generative Learning Successful generation of diverse characters and animations Structure-consistent Prediction GANs (SPGAN) Progressive Structure-conditional GANs (PSGAN)Structure-Aware Generative Learning Anime Inbetweening Interpolation between frames with large structural movement Anime Generation with DeNA AI
  • 13. We will talk about: - Progress and challenges in cutting-edge image generation - A solution by DeNA AI’s Structure-Aware Generative Learning Anime Generation with DeNA AI
  • 14. 2010 – ML for Games Launched ML group at DeNA. Applied ML/DM to improve games 2011 – ML for the Gaming Platform ‘Mobage’ (51 million users) Developed dozens of distributed ML systems for a game platform 2014 – present: ML for All Services at DeNA Develop ML systems for a wide range of services Social Network MangaGaming Platform ChatbotNews Launched the Group for Machine Learning (ML) at DeNA in 2010 Have developed a broad range of services utilizing ML for over 9 years Examples: Koichi Hamada (@hamadakoichi)
  • 15. Ph.D. in Theoretical Physics (Quantum and Statistical Field Theory) Book: “Technologies that support the large-scale social gaming platform Mobage” (Best Book Award in CEDEC 2014) Founder - TokyoWebmining Community (February 2010) - Objective: Expand the fields of practical applications of Machine Learning - 1,500 registered participants with over 60 organized meet-ups Launched the Group for Machine Learning (ML) at DeNA in 2010 Have developed a broad range of services utilizing ML for over 9 years Koichi Hamada (@hamadakoichi)
  • 16. 5. Design Interfaces Service Front End 2. Design User Experiences 4. Design Auto Refinement Cycles 3. Design Services 7. Design Distributed Algorithms 8. Implement Distributed Algorithms Distributed Back End YARN HDFS GPU 1. Research and Develop AI Models New Valuable User Experiences My activities: Have designed and developed new valuable experiences and services utilizing AI Koichi Hamada (@hamadakoichi) 6. Design Logging
  • 17. Designs, Implementations, Demonstration Experiments, Research Paper Publications, Practical Applications, and Project Promotion Generated Anime Koichi Hamada (@hamadakoichi) AI Anime Generation Project AI Development and Project Lead AI Generated Results for Anime Inbetweening on “Zunda Horizon*” Test Data**: https://youtu.be/X9j1fwexK2c?t=4 Input Frames AI Generated Frames (x16 Generation) **Trained using DeNA Dataset which does not include “Zunda Horizon” data*SSS STL WAO 2017 “Zunda Horizon”
  • 18. Anime Inbetweening with SPGAN Anime Generation with PSGAN AGENDA Recent Progress on Image Generation and Issues Conclusion - Anime Generation with AI - Overview Our Approaches and Contributions Other AI Solutions for Anime Production Issues
  • 19. Question: Which image was generated by AI?
  • 20. 1 3 5 7 2 4 6 8 Question: Which image was generated by AI?
  • 21. Question: Which image was generated by AI? AI Real Photos 1 3 5 7 2 4 6 8 Answer: All of the top images
  • 22. Question: Which image was generated by AI? Answer: All of the top images ProgressiveGAN (Karras et al., ICLR 2018) BigGAN (Brock et al., ICLR 2019) 1 3 5 7 2 4 6 8 AI Real Photos
  • 23. High-resolution and high-quality image generation by AI AI-generated images have become higher resolution and quality and are harder to distinguish from real photos ProgressiveGAN (Karras et al., ICLR 2018) BigGAN (Brock et al., ICLR 2019)
  • 24. High-resolution and high-quality image generation by AI AI-generated images have become higher resolution and quality and are harder to distinguish from real photos ProgressiveGAN (Karras et al., ICLR 2018) BigGAN (Brock et al., ICLR 2019)
  • 25. High-resolution and high-quality image generation by AI AI-generated images have become higher resolution and quality and are harder to distinguish from real photos ProgressiveGAN (Karras et al., ICLR 2018) BigGAN (Brock et al., ICLR 2019)
  • 27. Generator and Discriminator compete and improve the generation quality Generative Adversarial Networks (GANs) Discriminator: classifies the input data as either real or fake Generator: attempts to fool the Discriminator by generating realistic images Generative Adversarial Nets. Ian J. Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde- Farley, Sherjil Ozair, Aaron Courville, Yoshua Bengio. arXiv:1406.2661. In NIPS 2014.
  • 28. Generator and Discriminator compete and improve the generation quality Generative Adversarial Networks (GANs) Minimax Objective function Discriminator classifies the real data as ‘real’ (Goodfellow+, NIPS2014, Deep Learning Workshop, Presentation) Discriminator classifies the generated data as ‘fake’ Discriminator tries to classify correctly (maximize) Generator tries to fool Discriminator(minimize)
  • 29. High-resolution and high-quality image generation with GANs AI-generated images have become higher resolution and quality and are harder to distinguish from real photos ProgressiveGAN (Karras et al., ICLR 2018) BigGAN (Brock et al., ICLR 2019)
  • 30. High-resolution and high-quality image generation with GANs AI-generated images have become higher resolution and quality and are harder to distinguish from real photos ProgressiveGAN (Karras et al., ICLR 2018) BigGAN (Brock et al., ICLR 2019)
  • 31. Progressive GAN (Karras+, ICLR'18) Progressive growth of Generator and Discriminator Stable generation of 1024 x 1024 images Generated Images (1024X1024) Generated Images (256x256) Progressive Growing of GANs for Improved Quality, Stability, and Variation Tero Karras, Timo Aila, Samuli Laine, Jaakko Lehtinen. In ICLR 2018.
  • 32. https://youtu.be/XOxxPcy5Gr4?t=1m47s Progressive Growing of GANs for Improved Quality, Stability, and Variation Tero Karras, Timo Aila, Samuli Laine, Jaakko Lehtinen. In ICLR 2018. Progressive GAN (Karras+, ICLR'18)
  • 33. https://youtu.be/XOxxPcy5Gr4?t=4m Progressive Growing of GANs for Improved Quality, Stability, and Variation Tero Karras, Timo Aila, Samuli Laine, Jaakko Lehtinen. In ICLR 2018. Progressive GAN (Karras+, ICLR'18)
  • 34. High-resolution and high-quality image generation with GANs AI-generated images have become higher resolution and quality and are harder to distinguish from real photos ProgressiveGAN (Karras et al., ICLR 2018) BigGAN (Brock et al., ICLR 2019)
  • 35. High-resolution and high-quality image generation with GANs AI-generated images have become higher resolution and quality and are harder to distinguish from real photos ProgressiveGAN (Karras et al., ICLR 2018) BigGAN (Brock et al., ICLR 2019)
  • 36. BigGAN (Brock+, ICLR'19) Class conditional image generation Diverse and high-quality image generation using ImageNet + Spectral Normalization on Generator + Self Attention + Two Time Scale Update Rule Generated Images (512x512) + Spectral Normalization on Discriminator + Projection Discriminator SNGAN with Projection (Miyato+, ICLR’18) SAGAN (Zhang+, 18) BigGAN (Brock+, ICLR’19) + Large Batch Size (256→2048) + Large Channel (64→96) + Shared Embedding + Hierarchical Latent Space + Truncation Trick + Orthogonal Regularization + First Singular Value Clamp + Zero-centered Gradient Penalty Large Scale GAN Training for High Fidelity Natural Image Synthesis. Andrew Brock, Jeff Donahue, Karen Simonyan. arXiv:1809.11096. In ICLR 2018.
  • 37. BigGAN (Brock+, ICLR'19) Class conditional image generation Diverse and high-quality image generation using ImageNet Generator Typical Architecture Res Block Architecture for ImageNet at 512x512 Large Scale GAN Training for High Fidelity Natural Image Synthesis. Andrew Brock, Jeff Donahue, Karen Simonyan. arXiv:1809.11096. In ICLR 2019. Generated Images (512x512)
  • 38. BigGAN (Brock+, ICLR'19) Large Scale GAN Training for High Fidelity Natural Image Synthesis. Andrew Brock, Jeff Donahue, Karen Simonyan. arXiv:1809.11096. In ICLR 2019. Generates high-fidelity and diverse images using ImageNet with 1000 classes Generated Images (512x512)
  • 39. BigGAN (Brock+, ICLR'19) Large Scale GAN Training for High Fidelity Natural Image Synthesis. Andrew Brock, Jeff Donahue, Karen Simonyan. arXiv:1809.11096. In ICLR 2019. Generates high-fidelity and diverse images using ImageNet with 1000 classes Generated Images (512x512)
  • 40. BigGAN (Brock+, ICLR'19) Large Scale GAN Training for High Fidelity Natural Image Synthesis. Andrew Brock, Jeff Donahue, Karen Simonyan. arXiv:1809.11096. In ICLR 2019. Generates high-fidelity and diverse images using ImageNet with 1000 classes Generated Images (512x512)
  • 41. BigGAN (Brock+, ICLR'19) Large Scale GAN Training for High Fidelity Natural Image Synthesis. Andrew Brock, Jeff Donahue, Karen Simonyan. arXiv:1809.11096. In ICLR 2019. Generates high-fidelity and diverse images using ImageNet with 1000 classes Generated Images (512x512)
  • 42. BigGAN (Brock+, ICLR'19) Generates high-fidelity and diverse images using ImageNet with 1000 classes Generated Images (512x512) Large Scale GAN Training for High Fidelity Natural Image Synthesis. Andrew Brock, Jeff Donahue, Karen Simonyan. arXiv:1809.11096. In ICLR 2019.
  • 43. BigGAN (Brock+, ICLR'19) Large Scale GAN Training for High Fidelity Natural Image Synthesis. Andrew Brock, Jeff Donahue, Karen Simonyan. arXiv:1809.11096. In ICLR 2019. Generates high-fidelity and diverse images using ImageNet with 1000 classes Generated Images (512x512)
  • 44. BigGAN (Brock+, ICLR'19) Large Scale GAN Training for High Fidelity Natural Image Synthesis. Andrew Brock, Jeff Donahue, Karen Simonyan. arXiv:1809.11096. In ICLR 2019. Generates high-fidelity and diverse images using ImageNet with 1000 classes Generated Images (512x512)
  • 45. High-resolution and high-quality image generation with GANs ProgressiveGAN (Karras et al., ICLR 2018) BigGAN (Brock et al., ICLR 2019) AI-generated images have become higher resolution and quality and are harder to distinguish from real photos
  • 46. High-resolution and high-quality image generation with GANs AI-generated images have become higher resolution and quality and are harder to distinguish from real photos However, full-body image generation with complex structures has been a challenge ProgressiveGAN (Karras et al., ICLR 2018) BigGAN (Brock et al., ICLR 2019)
  • 47. High-resolution and high-quality image generation with GANs ProgressiveGAN (Karras et al., ICLR 2018) BigGAN (Brock et al., ICLR 2019) AI-generated images have become higher resolution and quality and are harder to distinguish from real photos However, full-body image generation with complex structures has been a challenge
  • 48. High-resolution and high-quality image generation with GANs ProgressiveGAN (Karras et al., ICLR 2018) BigGAN (Brock et al., ICLR 2019) Applications for Anime Production Limited to some specific cases, such as - Generation for specific body parts (e.g. Face) - Colorization (which does not treat structural generation) AI-generated images have become higher resolution and quality and are harder to distinguish from real photos However, full-body image generation with complex structures has been a challenge
  • 49. Anime Inbetweening with SPGAN Anime Generation with PSGAN AGENDA Recent Progress on Image Generation and Issues Conclusion - Anime Generation with AI - Overview Our Approaches and Contributions Other AI Solutions for Anime Production Issues
  • 50. Anime Generation with DeNA AI Generated Anime 4x4 4x4 1024x1024 4x4 4x4 Latent Real Condition 1024x1024 1024x1024 1024x1024 512x512 512x512 1024x1024 Add animation to the new character by imposing a pose sequence Generation of brand new characters Progressive Structure-conditional GANs (PSGAN) Generated Full-body High-resolution Anime Generation with Progressive Structure-conditional Generative Adversarial Networks. Koichi Hamada, Kentaro Tachibana, Tianqi Li, Hiroto Honda, and Yusuke Uchida. In ECCV Workshop 2018. Successful image generation of full-body and high-resolution characters Diverse characters and anime generation https://youtu.be/X9j1fwexK2c?t=104Generated Anime:
  • 51. DeNA AI: Diverse Characters and Anime Generation https://youtu.be/bIi5gSITK0EFull-body anime generation with Progressive Structure-conditional GANs Generated results: Brand new characters
  • 52. DeNA AI: Diverse Characters and Anime Generation https://youtu.be/0LQlfkvQ3OkAdding action to full-body anime characters with Progressive Structure-conditional GANs Can add animation to the new character by specifying a sequence of 2D poses
  • 53. Challenges toward Anime Generation with Deep Generative Models Koichi Hamada and Tianqi Li. In DeNA TechCon 2019. Successful video interpolation between frames with large structural movement Anime inbetweening DeNA AI: Anime Inbetweening Structure-consistent Prediction GANs (SPGAN) Input SPGAN (Ours) SOTA model Deep Voxel Flow Deep Voxel Flow (ICCV’17) Deep Voxel Flow (ICCV'17) PSNR SSIM Structured displacement SPGAN (Ours) SPGAN (Ours) Structural displacementStructural displacement https://youtu.be/X9j1fwexK2c?t=132Generated Anime:
  • 54. DeNA AI: Anime Inbetweening Can inbetween frames with large structural movement (e.g. turning around) Inbetweening of frames with small movement SOTA model Deep Voxel FlowInput SPGAN (Ours) Inbetweening of frames with large movement https://youtu.be/vXVr64BbXHYExperimental Results: “Anime Frame Generation with Structure-consistent Prediction GANs” https://youtu.be/X9j1fwexK2c?t=139Video:
  • 55. DeNA AI: Anime Inbetweening step size = 1 step size = 4 step size = 7 step size = 10 Input SPGAN (Ours) SoTA Deep Voxel Flow (ICCV’17) Can inbetween frames with large structural movement with good structural and time consistency Small Structural displacement Large https://youtu.be/vXVr64BbXHYExperimental Results: “Anime Frame Generation with Structure-consistent Prediction GANs” https://youtu.be/X9j1fwexK2c?t=150Video:
  • 56. DeNA AI: Anime Inbetweening Deep Voxel Flow Ours Average PSNR/SSIM on test dataset (step size=4) PSNR SSIM Deep Voxel Flow 23.32 0.9294 SPGAN (Ours) 24.27 0.9407 SPGAN (Ours) Can inbetween frames with large structural movement with good structural and time consistency PSNR SSIM
  • 57. Successful image generation with detailed textures for each structural element Anime generation with a few images DeNA AI: Anime generation with a few images Structural Feature-embedding GANs (SFGAN) Rough designation (Structure designation) Generated result Rough designation (Structure designation) Generated result Image (1 frame) Image (1 frame) https://youtu.be/X9j1fwexK2c?t=166Generated Anime:
  • 58. Successful image generation with detailed textures for each structural element Anime generation with a few images DeNA AI: Anime generation with a few images Can generate diverse body type, clothing, etc. with rough designation Structural Feature-embedding GANs (SFGAN) Rough designation (Structure designation) Generated result Rough designation (Structure designation) Generated result Image (1 frame) Image (1 frame) https://youtu.be/X9j1fwexK2c?t=166Generated Anime:
  • 59. Successful landscape generation with designated detailed texture for each part Background art generation DeNA AI: Background art generation Structural Feature-embedding GANs (SFGAN) Image (1 frame) SFGAN (Ours)Layout SoTA model SPADE (CVPR’19) Generated Result
  • 60. Successful colorization that exactly reflects color example and line details Exact colorization based on colorized example DeNA AI: Exact colorization Structural Feature-embedding GANs (SFGAN) Colorized example (1 frame) Colorized resultLines Rough https://youtu.be/X9j1fwexK2c?t=191Generated Anime:
  • 61. Structure-Aware Generative Learning DeNA AI Development of AI Anime Generation
  • 62. Anime Generation with DeNA AI Structure-Aware Generative Learning Successful generation of diverse characters and animations
  • 63. Anime Generation with DeNA AI Our Solution Challenge Back- ground Structure-Aware Generative Learning Successful generation of diverse characters and animations
  • 64. In 2018, AI generates high-quality images hard to distinguish from real photos Anime Generation with DeNA AI Our Solution Challenge Back- ground Structure-Aware Generative Learning Successful generation of diverse characters and animations
  • 65. In 2018, AI generates high-quality images hard to distinguish from real photos Anime Generation High-quality image generation with complex structures Anime Generation with DeNA AI Our Solution Challenge Back- ground Structure-Aware Generative Learning Successful generation of diverse characters and animations
  • 66. In 2018, AI generates high-quality images hard to distinguish from real photos Anime Generation High-quality image generation with complex structures Anime Generation with DeNA AI Our Solution Challenge Back- ground Structure-Aware Generative Learning Successful generation of diverse characters and animations Anime Inbetweening Interpolation between frames with large structural movement
  • 67. In 2018, AI generates high-quality images hard to distinguish from real photos Anime Generation High-quality image generation with complex structures Progressive Structure-conditional GANs (PSGAN) Anime Generation with DeNA AI Our Solution Challenge Back- ground Structure-Aware Generative Learning Successful generation of diverse characters and animations Structure-consistent Prediction GANs (SPGAN) Progressive Structure-conditional GANs (PSGAN)Structure-Aware Generative Learning Anime Inbetweening Interpolation between frames with large structural movement
  • 68. Anime Inbetweening with SPGAN Anime Generation with PSGAN AGENDA Recent Progress on Image Generation and Issues Conclusion - Anime Generation with AI - Overview Our Approaches and Contributions Other AI Solutions for Anime Production Issues
  • 69. High-resolution and high-quality image generation with GANs ProgressiveGAN (Karras et al., ICLR 2018) BigGAN (Brock et al., ICLR 2019) Applications for Anime Production have been limited to some specific cases, such as - Generation for specific body parts (e.g. Face) - Colorization (which does not treat structural generation) AI-generated images have become higher resolution and quality and are harder to distinguish from real photos However, full-body image generation with complex structures has been a challenge
  • 70. In 2018, AI generates high-quality images hard to distinguish from real photos Anime Generation High-quality image generation with complex structures Progressive Structure-conditional GANs (PSGAN) Anime Generation with DeNA AI Our Solution Challenge Back- ground Structure-Aware Generative Learning Successful generation of diverse characters and animations Structure-consistent Prediction GANs (SPGAN) Progressive Structure-conditional GANs (PSGAN)Structure-Aware Generative Learning Anime Inbetweening Interpolation between frames with large structural movement
  • 71. Proposed method: Progressive Structure-conditional GANs (PSGAN) Structure-Aware Generative Learning Full-body High-resolution Anime Generation with Progressive Structure-conditional Generative Adversarial Networks Koichi Hamada, Kentaro Tachibana, Tianqi Li, Hiroto Honda, and Yusuke Uchida. In ECCV Workshop 2018.
  • 72. Anime Generation: Progressive Structure-conditional GANs (PSGAN) (Hamada+, ECCVW 2018) Image generation of full-body and high-resolution characters which has been a challenge due to its complex structure Generated anime characters (1024x1024) https://youtu.be/bIi5gSITK0E Generation of brand new characters Add animation to the new character by imposing a pose sequence https://youtu.be/0LQlfkvQ3Ok Full-body High-resolution Anime Generation with Progressive Structure-conditional Generative Adversarial Networks Koichi Hamada, Kentaro Tachibana, Tianqi Li, Hiroto Honda, and Yusuke Uchida. In ECCV Workshop 2018.
  • 73. Image generation of full-body and high-resolution characters which has been a challenge due to its complex structure Diverse characters and anime generation Anime Generation: Progressive Structure-conditional GANs (PSGAN) (Hamada+, ECCVW 2018) Generated anime characters (1024x1024) https://youtu.be/bIi5gSITK0E Generation of brand new characters Add animation to the new character by imposing a pose sequence https://youtu.be/0LQlfkvQ3Ok Full-body High-resolution Anime Generation with Progressive Structure-conditional Generative Adversarial Networks Koichi Hamada, Kentaro Tachibana, Tianqi Li, Hiroto Honda, and Yusuke Uchida. In ECCV Workshop 2018.
  • 74. Proposed method: Progressive Structure-conditional GANs (PSGAN) Learn to generate structure and image simultaneously Stabilize generative learning of complex structures by progressive network growth 4x4 4x4 1024x1024 4x4 4x4 Latent Real Condition 1024x1024 1024x1024 Generated 1024x1024 512x512 512x512 1024x1024
  • 75. Proposed method: Progressive Structure-conditional GANs (PSGAN) 4x4 4x4 4x4 4x4 Latent Real Condition 4x4 4x44x4 Generated Structure and image generation at low resolution for high-level context
  • 76. Proposed method: Progressive Structure-conditional GANs (PSGAN) 4x4 4x4 8x8 4x4 8x8 4x4 Latent Real Condition 8x8 8x88x8 Generated Structure and image generation at low resolution for high-level context Increase resolution in a step-by-step manner to progressively learn to generate the detail structures
  • 77. Proposed method: Progressive Structure-conditional GANs (PSGAN) Structure and image generation at low resolution for high-level context Increase resolution in a step-by-step manner to progressively learn to generate the detail structures 4x4 4x4 1024x1024 4x4 4x4 Latent Real Condition 1024x1024 1024x1024 Generated 1024x1024 512x512 512x512 1024x1024
  • 78. Avatar Anime Dataset A novel dataset containing diverse character images and 2D poses
  • 79. Avatar Anime Dataset A novel dataset containing diverse character images and 2D poses Built by Unity 3D Avatar models and motions
  • 80. Avatar Anime Dataset Avatar Play A novel dataset containing diverse character images and 2D poses Built by Unity 3D Avatar models and motions Developed utilizing 100 thousand 3D Avatar assets on the Mobage service
  • 81. Generated Images: Progressive Structure-conditional GANs (PSGAN) Image generation of full-body and high-resolution characters which has been a challenge due to its complex structure Diverse characters and anime generation Generated anime characters (1024x1024) https://youtu.be/bIi5gSITK0E Generation of brand new characters Add animation to the new character by imposing a pose sequence https://youtu.be/0LQlfkvQ3Ok
  • 82. Generated Images: Progressive Structure-conditional GANs (PSGAN) https://youtu.be/bIi5gSITK0EFull-body anime generation at 1024x1024 with Progressive Structure-conditional GANs Generated results of brand new characters Generated Anime (1024x1024)
  • 83. Generated Images: Progressive Structure-conditional GANs (PSGAN) https://youtu.be/0LQlfkvQ3OkAdding action to full-body anime characters with Progressive Structure-conditional GANs Add animation to the new character by imposing a pose sequence Generated Anime (1024x1024)
  • 84. Generated Images: Progressive Structure-conditional GANs (PSGAN) (ICLR’18) Structure Consistency: PSGAN’s images are more structure-consistent
  • 85. Generated Images: Progressive Structure-conditional GANs (PSGAN) (ICLR’18) (NIPS’17) (NIPS’17) Structure Consistency: PSGAN’s images are more structure-consistent Image Quality on Pose Conditions: more detailed and high-quality
  • 86. Generated Images: Progressive Structure-conditional GANs (PSGAN) Generated Images Application for realistic images: Generation of new clothes with indicated pose
  • 87. In 2018, AI generates high-quality images hard to distinguish from real photos Anime Generation High-quality image generation with complex structures Progressive Structure-conditional GANs (PSGAN) Anime Generation with DeNA AI Our Solution Challenge Back- ground Structure-Aware Generative Learning Successful generation of diverse characters and animations Structure-consistent Prediction GANs (SPGAN) Progressive Structure-conditional GANs (PSGAN)Structure-Aware Generative Learning Anime Inbetweening Interpolation between frames with large structural movement
  • 88. In 2018, AI generates high-quality images hard to distinguish from real photos Anime Generation High-quality image generation with complex structures Progressive Structure-conditional GANs (PSGAN) Our Solution Challenge Back- ground Structure-Aware Generative Learning Successful generation of diverse characters and animations Structure-consistent Prediction GANs (SPGAN) Progressive Structure-conditional GANs (PSGAN)Structure-Aware Generative Learning Anime Inbetweening Interpolation between frames with large structural movement Anime Generation with DeNA AI
  • 89. Anime Inbetweening with SPGAN Anime Generation with PSGAN AGENDA Recent Progress on Image Generation and Issues Conclusion - Anime Generation with AI - Overview Our Approaches and Contributions Other AI Solutions for Anime Production Issues
  • 91. Anime Inbetweening Problems faced in Anime Production Animator Web Report (in Japanese) (http://animatorweb.jp/)
  • 92. • Limited time • Limited budget • Limited human resources • Quality demands Anime Inbetweening Problems faced in Anime Production Animator Web Report (in Japanese) (http://animatorweb.jp/)
  • 93. Anime inbetweening by animators Anime Inbetweening Animator Web Report (in Japanese) (http://animatorweb.jp/)
  • 94. Anime Inbetweening * Anime inbetweening by animators original 1 original 2 *SSS STL WAO 2017 “Zunda Horizon” Animator Web Report (in Japanese) (http://animatorweb.jp/)
  • 95. Anime Inbetweening original 1 original 2inbetweened frames * Anime inbetweening by animators *SSS STL WAO 2017 “Zunda Horizon” Animator Web Report (in Japanese) (http://animatorweb.jp/)
  • 96. Anime Inbetweening • Animators have to draw 3500-4000 inbetweens per one 30- min anime episode * Anime inbetweening by animators original 1 original 2inbetweened frames *SSS STL WAO 2017 “Zunda Horizon” Animator Web Report (in Japanese) (http://animatorweb.jp/)
  • 97. Anime Inbetweening • Animators have to draw 3500-4000 inbetweens per one 30- min anime episode • So much effort - hours to draw one inbetween * Anime inbetweening by animators original 1 original 2inbetweened frames *SSS STL WAO 2017 “Zunda Horizon” Animator Web Report (in Japanese) (http://animatorweb.jp/)
  • 98. Anime Inbetweening * • Animators have to draw 3500-4000 inbetweens per one 30- min anime episode • So much effort - hours to draw one inbetween original 1 original 2inbetweened frames *SSS STL WAO 2017 “Zunda Horizon” Animator Web Report (in Japanese) (http://animatorweb.jp/) Anime inbetweening by animators
  • 100. Anime Inbetweening )3 Frame Interpolation 3 Frame Automating anime inbetweening
  • 101. Anime Inbetweening )3 Frame Interpolation 3 Frame Automating anime inbetweening
  • 103. Automating anime inbetweening Multi Frame Interpolation Anime Inbetweening AI
  • 105. State-of-the-art frame interpolation method Frame Interpolation
  • 106. State-of-the-art frame interpolation method Frame Interpolation Super SloMo (Jiang+, CVPR’18) Super SloMo: High Quality Estimation of Multiple Intermediate Frames for Video Interpolation. Huaizu Jiang, Deqing Sun, Varun Jampani, Ming-Hsuan Yang, Erik Learned-Miller, Jan Kautz. In CVPR 2018.
  • 107. State-of-the-art frame interpolation method Frame Interpolation Super SloMo (Jiang+, CVPR’18) • Infer the intermediate frame from the input frame sequences at 30/60FPS -> generate 240/480FPS (x8) video Super SloMo: High Quality Estimation of Multiple Intermediate Frames for Video Interpolation. Huaizu Jiang, Deqing Sun, Varun Jampani, Ming-Hsuan Yang, Erik Learned-Miller, Jan Kautz. In CVPR 2018. https://youtu.be/MjViy6kyiqs Research at NVIDIA: Transforming Standard Video Into Slow Motion with AI
  • 108. State-of-the-art frame interpolation method Frame Interpolation Deep Voxel Flow (Liu+, ICCV’17) Video Frame Synthesis using Deep Voxel Flow. Ziwei Liu, Raymond A. Yeh, Xiaoou Tang, Yiming Liu, Aseem Agarwala. In ICCV 2017.
  • 109. State-of-the-art frame interpolation method Frame Interpolation Deep Voxel Flow (Liu+, ICCV’17) • Generate a 60fps video out of a 30FPS video Video Frame Synthesis using Deep Voxel Flow. Ziwei Liu, Raymond A. Yeh, Xiaoou Tang, Yiming Liu, Aseem Agarwala. In ICCV 2017. https://youtu.be/qNXPI01WlBU?t=30s Video Frame Synthesis using Deep Voxel Flow
  • 110. State-of-the-art frame interpolation method Frame Interpolation Super SloMo (Jiang+, CVPR’18) • Calculate Optical Flow-> synthesize intermediate frame-> refine • Generate a 240/480FPS video out of a 30/60FPS video Deep Voxel Flow (Liu+, ICCV’17) • Calculate Optical Flow-> synthesize intermediate frame • Competitive performance as Super SloMo Super SloMo(Adobe) Super SloMo Deep Voxel Flow Video Frame Synthesis using Deep Voxel Flow. Ziwei Liu, Raymond A. Yeh, Xiaoou Tang, Yiming Liu, Aseem Agarwala. In ICCV 2017. Super SloMo: High Quality Estimation of Multiple Intermediate Frames for Video Interpolation. Huaizu Jiang, Deqing Sun, Varun Jampani, Ming-Hsuan Yang, Erik Learned-Miller, Jan Kautz. In CVPR 2018. Calculate Optical flow and Frame interpolation using Neural Networks
  • 111. Frame Interpolation Optical Flow Vector map representing displacement (movement) of points between two consecutive frames High intensity = Large displacement
  • 112. Issues of the frame interpolation methods
  • 113. Frame Interpolation does not work for anime inbetweening Issue : Anime Inbetweening Frame interpolation for frames with large structural displacement is key. n Existing methods: High-FPS input (30 60 → 240 480) n Anime Inbetweening: Low-FPS input (3 7 → 12 30) * *SSS STL WAO 2017 “Zunda Horizon”
  • 114. Frame Interpolation does not work for anime inbetweening Issue : Anime Inbetweening n Existing methods: Photo real n Anime Inbetweening: Illustration * Video Optical-flow Illustration style is monotone in color, low textured -> Difficult to calculate Optical Flow. *SSS STL WAO 2017 “Zunda Horizon”
  • 115. Frame Interpolation does not work for anime inbetweening Issue : Anime Inbetweening Super SloMo Deep Voxel Flow … Anime Inbetweening Photo real Illustration high-fps input low-fps input
  • 116. Proposed method: Structure-consistent Prediction GANs (SPGAN) Structure-Aware Generative Learning Challenges toward Anime Generation with Deep Generative Models Koichi Hamada and Tianqi Li. In DeNA TechCon 2019.
  • 117. A multi-task training using structural information and optical flow Proposed method: Structure-consistent Prediction GANs (SPGAN) n Input frames: Multi-task training - Pose Keypoints: n Optical Flow: n Structure Information: - Body-part masks:
  • 118. Proposed method: Structure-consistent Prediction GANs (SPGAN)- pipeline Structure Information G I0 I4 D Optical Flow I1, I2, I3 (Generated) Ground Truth MSE MSE Ground TruthStructure Information (Generated) A multi-task training using structural information and optical flow
  • 119. Proposed method: Structure-consistent Prediction GANs (SPGAN)- Discriminator Improve generation quality using two Discriminators
  • 120. Proposed method: Structure-consistent Prediction GANs (SPGAN)- Discriminator Conv-BN-ReLU Conv-BN-ReLU Conv-BN-ReLU Conv-BN-ReLU Local Discriminator “Real” or “Fake” Local Patch (16×16pix) Improve quality of details and time consistency by Local Discriminator and Temporal Discriminator
  • 121. Proposed method: Structure-consistent Prediction GANs (SPGAN)- Discriminator Conv-BN-ReLU Conv-BN-ReLU Generated Image Sequence Conv-BN-ReLU Conv-BN-ReLU Conv-BN-ReLU Conv-BN-ReLU Conv-BN-ReLU Conv-BN-ReLU Conv-BN-ReLU FC Local Discriminator Temporal Discriminator “Real” or “Fake” Local Patch (16×16pix) Image Sequence “Real” or “Fake” Improve quality of details and time consistency by Local Discriminator and Temporal Discriminator
  • 123. Experiment settings Extract five consecutive frames from a video and infer intermediate 3 frames using only the first and the last frames Video
  • 124. Experiment settings Extract five consecutive frames from a video and infer intermediate 3 frames using only the first and the last frames image0 image1 image2 image3 image4Video
  • 125. Experiment settings Experiments using different frame steps (different fps and structural displacement settings) ⁃ step size = 4 (7FPS -> 30FPS): 001.png, 005.png, 009.png, 013.png, 017.png ⁃ step size = 1 (30FPS -> 120FPS): 001.png, 002.png, 003.png, 004.png, 005.png
  • 126. Experiment settings ⁃ step size = 4 (7FPS -> 30FPS): 001.png, 005.png, 009.png, 013.png, 017.png ⁃ step size = 1 (30FPS -> 120FPS): 001.png, 002.png, 003.png, 004.png, 005.png Experiments using different frame steps (different fps and structural displacement settings)
  • 128. Generated Results: Structure-consistent Prediction GANs (SPGAN) Proposed method can interpolate the frames having large displacement with good structural and time consistency interpolation of frames with small movement SOTA model Deep Voxel FlowInput SPGAN (Ours) interpolation of frames with large movement Experimental Results: “Anime Frame Generation with Structure-consistent Prediction GANs” https://youtu.be/vXVr64BbXHY https://youtu.be/X9j1fwexK2c?t=139Video:
  • 129. Generated Results: Structure-consistent Prediction GANs (SPGAN) step size = 1 step size = 4 step size = 7 step size = 10 Input SPGAN (Ours) SoTA Deep Voxel Flow (ICCV’17) Proposed method can interpolate the frames having large displacement with good structural and time consistency Small Structural displacement Large Experimental Results: “Anime Frame Generation with Structure-consistent Prediction GANs” https://youtu.be/vXVr64BbXHY https://youtu.be/X9j1fwexK2c?t=150Video:
  • 130. Quantitative Evaluations: Structure-consistent Prediction GANs(SPGAN) Deep Voxel Flow Ours Average PSNR/SSIM on test dataset (step size=4) PSNR SSIM Deep Voxel Flow 23.32 0.9294 SPGAN(Ours) 24.27 0.9407 SPGAN (Ours) Proposed method can interpolate the frames having large displacement with good structural and time consistency
  • 131. Anime Inbetweening with SPGAN Anime Generation with PSGAN AGENDA Recent Progress on Image Generation and Issues Conclusion - Anime Generation with AI - Overview Our Approaches and Contributions Other AI Solutions for Anime Production Issues
  • 132. Issues in anime production Today we will discuss the following five points Process Issues Overall process Handling 4K/60fps (Making large key animation default, and increasing number of inbetween frames) Increased difficulty of managing processes & progress due to more complex processes (2D, 3D, etc.), and separation of animation processes Create layout (LO) Insufficient key animation pipeline Create key animation frames (first) Insufficient key animation pipeline Create key animation frames (second) Insufficient key animation pipeline Animation supervising (characters) Greater burden on animation supervising for characters due to more complex character design Animation supervising (action) Insufficient key animation pipeline Create inbetweens Reduced pipeline & higher costs from overseas production companies Finishing Reduced pipeline & higher costs from overseas production companies In-between check Demands to shorten check time in response to lengthened lead time for animation (reduced post production time) Background art Background / art delivery timing tending to be delayed, with more shoots 3D Lack of 3D animators and increased investment in education for training Issues
  • 133. DeNA AI: Overall process/ Animation (Inbetweens) Input Frames AI Generated Frames (x16 Generation) x16 high-quality anime inbetweening This makes creating 4K/60FPS animation easier AI Generated Anime Inbetweening on Zunda Horizon* Test Data** Our Generated Results: https://youtu.be/X9j1fwexK2c?t=4AI Generated Results for Anime Inbetweening on “Zunda Horizon*” Test Data**: **Trained using DeNA Dataset which does not include “Zunda Horizon” data*SSS STL WAO 2017 “Zunda Horizon”
  • 134. Character drawn in new pose by designating style and drawing 2D stick figure Changing the 2D stick figure makes the character move in accordance with 3D structure This makes creating key animation easier Character designation Structuredesignation (2Dposeinformation) Generated examples DeNA AI: Key Animation Frame/ Animation (Inbetweens) https://youtu.be/X9j1fwexK2c?t=104Our Contribution:
  • 135. Character drawn in new pose by designating style and drawing 2D stick figure Changing the 2D stick figure makes the character move in accordance with 3D structure This makes creating key animation easier DeNA AI: Key Animation Frame/ Animation (Inbetweens) Designate 2D pose series to animate the new characterNew character generation https://youtu.be/bIi5gSITK0E https://youtu.be/0LQlfkvQ3Ok https://youtu.be/Gz90H1M7_u4?t=50Video:https://youtu.be/X9j1fwexK2c?t=104Our Contribution:
  • 136. Animation generation with a few images Animation generated by designating roughs This makes creating key animation & inbetweens easier Image (1 frame) Rough designation (structure designation) Image (1 frame) Generated result Rough designation (structure designation) Generated result DeNA AI: Key Animation Frame/ Animation (Inbetweens) https://youtu.be/X9j1fwexK2c?t=166Our Contribution:
  • 137. Image (1 frame) Rough designation (structure designation) Image (1 frame) Generated result Rough designation (structure designation) Generated result Animation generation with a few images Animation generated by designating roughs This makes creating key animation & inbetweens easier DeNA AI: Key Animation Frame/ Animation (Inbetweens) https://youtu.be/X9j1fwexK2c?t=166Our Contribution: https://youtu.be/Gz90H1M7_u4?t=70Video:
  • 138. Automated coloring reflecting color sample and line details This makes finishing easier Colorized example (1 frame) Generated resultRoughLines https://youtu.be/X9j1fwexK2c?t=191Our Contribution: https://youtu.be/Gz90H1M7_u4?t=80Video: DeNA AI: Finishing (Colorization)
  • 139. Designate layout from art designation image and generate background art with detailed textures from each structural element Background automatically generated by drawing layout Can allocate more time to drawing to raise background quality Art designation image (1 frame) Generated resultLayout https://youtu.be/X9j1fwexK2c?t=183Our Contribution: DeNA AI: Background Art
  • 140. Designate layout from art designation image and generate background art with detailed textures from each structural element Background automatically generated by drawing layout Can allocate more time to drawing to raise background quality Image (1 frame) SFGAN (Ours)Layout SoTA model SPADE (CVPR’19) Generated Result https://youtu.be/X9j1fwexK2c?t=183Our Contribution: DeNA AI: Background Art
  • 141. Anime Inbetweening with SPGAN Anime Generation with PSGAN AGENDA Recent Progress on Image Generation and Issues Conclusion - Anime Generation with AI - Overview Our Approaches and Contributions Other AI Solutions for Anime Production Issues
  • 142. Input Frames AI Generated Frames (x16 Generation) AI Anime Inbetweening for a wide variety of objects **Trained using DeNA Dataset which does not include “Zunda Horizon” data*SSS STL WAO 2017 “Zunda Horizon” Generated Anime: https://youtu.be/X9j1fwexK2c?t=4 AI Generated Anime Inbetweening on Zunda Horizon* Test Data**
  • 143. AI Generated Anime Inbetweening on Zunda Horizon* Test Data** Comparison with human animators **Trained using DeNA Dataset which does not include “Zunda Horizon” data*SSS STL WAO 2017 “Zunda Horizon” AI Generated Frames (x4 Generation) Actual Frames drawn by Human Animators (x4 Generation) Input Frames Generated Anime: https://youtu.be/X9j1fwexK2c?t=80
  • 144. High-resolution and high-quality image generation with GANs ProgressiveGAN (Karras et al., ICLR 2018) BigGAN (Brock et al., ICLR 2019) AI-generated images have become higher resolution and quality and are harder to distinguish from real photos However, full-body image generation with complex structures has been a challenge
  • 145. High-resolution and high-quality image generation with GANs ProgressiveGAN (Karras et al., ICLR 2018) BigGAN (Brock et al., ICLR 2019) Applications for Anime Production Limited to some specific cases, such as - Generation for specific body parts (e.g. Face) - Colorization (which does not treat structural generation) AI-generated images have become higher resolution and quality and are harder to distinguish from real photos However, full-body image generation with complex structures has been a challenge
  • 146. Anime Generation with DeNA AI Generated Anime 4x4 4x4 1024x1024 4x4 4x4 Latent Real Condition 1024x1024 1024x1024 1024x1024 512x512 512x512 1024x1024 Add animation to the new character by imposing a pose sequence Generation of brand new characters Progressive Structure-conditional GANs (PSGAN) Generated Full-body High-resolution Anime Generation with Progressive Structure-conditional Generative Adversarial Networks. Koichi Hamada, Kentaro Tachibana, Tianqi Li, Hiroto Honda, and Yusuke Uchida. In ECCV Workshop 2018. Successful image generation of full-body and high-resolution characters Diverse characters and anime generation https://youtu.be/X9j1fwexK2c?t=104Generated Anime:
  • 147. Successful video interpolation between frames with large structural movement Anime inbetweening Anime Generation with DeNA AI Input SPGAN (Ours) SOTA model Deep Voxel Flow Structure-consistent Prediction GANs (SPGAN) Deep Voxel Flow (ICCV’17) Deep Voxel Flow (ICCV'17) PSNR SSIM Structured displacement SPGAN (Ours) SPGAN (Ours) Structural displacementStructural displacement Challenges toward Anime Generation with Deep Generative Models. Koichi Hamada and Tianqi Li. In DeNA TechCon 2019. https://youtu.be/X9j1fwexK2c?t=132Generated Anime:
  • 148. Successful image generation with detailed textures for each structural element Anime generation with a few images Anime Generation with DeNA AI Structural Feature-embedding GANs (SFGAN) Rough designation (Structure designation) Generated result Rough designation (Structure designation) Generated result Image (1 frame) Image (1 frame) https://youtu.be/X9j1fwexK2c?t=166Generated Anime:
  • 149. Successful landscape generation with designated detailed texture for each part Background art generation Anime Generation with DeNA AI Structural Feature-embedding GANs (SFGAN) Image (1 frame) SFGAN (Ours)Layout SoTA model SPADE (CVPR’19) Generated Result
  • 150. Successful colorization that exactly reflects color example and line details Exact colorization based on colorized example Anime Generation with DeNA AI Colorized example (1 frame) Colorized resultLines Rough Structural Feature-embedding GANs (SFGAN) https://youtu.be/X9j1fwexK2c?t=191Generated Anime:
  • 151. In 2018, AI generates high-quality images hard to distinguish from real photos Anime Generation High-quality image generation with complex structures Progressive Structure-conditional GANs (PSGAN) Anime Generation with DeNA AI Our Solution Challenge Back- ground Structure-Aware Generative Learning Successful generation of diverse characters and animations Structure-consistent Prediction GANs (SPGAN) Progressive Structure-conditional GANs (PSGAN)Structure-Aware Generative Learning Anime Inbetweening Interpolation between frames with large structural movement
  • 152. There are great possibilities for AI-generated animation At DeNA, we challenge ourselves to provide new value in anime generation We would be happy if we could work together with you to create a better future for animation production ai@dena.com Please contact us @hamadakoichi Koichi Hamada Anime Generation with DeNA AI