The document discusses recent advances in generative adversarial networks (GANs) for image generation. It summarizes two influential GAN models: ProgressiveGAN (Karras et al., 2018) and BigGAN (Brock et al., 2019). ProgressiveGAN introduced progressive growing of GANs to produce high resolution images. BigGAN scaled up GAN training through techniques like large batch sizes and regularization methods to generate high fidelity natural images. The document also discusses using GANs to generate full-body, high-resolution anime characters and adding motion through structure-conditional GANs.
32. #denatechcon
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.
36. #denatechcon
Progressive Growing of GANs for Improved Quality, Stability, and Variation.
Tero Karras, Timo Aila, Samuli Laine, Jaakko Lehtinen. In ICLR 2018.
(1024X1024)
(256x256)
37. #denatechcon
.441 7 545 7 4 /
Progressive Growing of GANs for Improved Quality, Stability, and Variation
Tero Karras, Timo Aila, Samuli Laine, Jaakko Lehtinen. In ICLR 2018.
38. #denatechcon
/ 5. 44 5
Progressive Growing of GANs for Improved Quality, Stability, and Variation
Tero Karras, Timo Aila, Samuli Laine, Jaakko Lehtinen. In ICLR 2018.
41. #denatechcon
+ Spectral Normalization on Generator
+ Self Attention
+ Two Time Scale Update Rule
(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.
43. #denatechcon
(512x512)
Large Scale GAN Training for High Fidelity Natural Image Synthesis.
Andrew Brock, Jeff Donahue, Karen Simonyan. arXiv:1809.11096. In ICLR 2019.
44. #denatechcon
Large Scale GAN Training for High Fidelity Natural Image Synthesis.
Andrew Brock, Jeff Donahue, Karen Simonyan. arXiv:1809.11096. In ICLR 2019.
(512x512)
45. #denatechcon
Large Scale GAN Training for High Fidelity Natural Image Synthesis.
Andrew Brock, Jeff Donahue, Karen Simonyan. arXiv:1809.11096. In ICLR 2019.
(512x512)
46. #denatechcon
Large Scale GAN Training for High Fidelity Natural Image Synthesis.
Andrew Brock, Jeff Donahue, Karen Simonyan. arXiv:1809.11096. In ICLR 2019.
(512x512)
47. #denatechcon
(512x512)
Large Scale GAN Training for High Fidelity Natural Image Synthesis.
Andrew Brock, Jeff Donahue, Karen Simonyan. arXiv:1809.11096. In ICLR 2019.
48. #denatechcon
(512x512)
Large Scale GAN Training for High Fidelity Natural Image Synthesis.
Andrew Brock, Jeff Donahue, Karen Simonyan. arXiv:1809.11096. In ICLR 2019.
49. #denatechcon
Large Scale GAN Training for High Fidelity Natural Image Synthesis.
Andrew Brock, Jeff Donahue, Karen Simonyan. arXiv:1809.11096. In ICLR 2019.
(512x512)
114. #denatechcon
8 1 1
1
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.
115. #denatechcon
/30 480 6 2/81 4C
+ 60 2
• 8 ,
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
117. #denatechcon
N I 7 B7 =: B = P
77 = 7: :=D
• /0 (+ /0 ,
Video Frame Synthesis using Deep Voxel Flow.
Ziwei Liu, Raymond A. Yeh, Xiaoou Tang, Yiming Liu, Aseem Agarwala. In ICCV 2017.
BB F=CBC 67 ?. / 3: 1 B
Video Frame Synthesis using Deep Voxel Flow
118. #denatechcon
D
F 6 + 23C
• 1 76 , P SV P J IOM S R
• ( ,24 c SV P J ,24 cP
/ ++ C
• 1 76 , P J SV P
• 4 8 4 0 L a
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.
F