GAN Theory
Modifyingthe Optimization of GAN
| 题目 | 内容 |
| GAN | |
| DCGAN | |
| WGAN | |
| Least-square GAN | |
| Loss Sensitive GAN | |
| Energy-based GAN | |
| Boundary-seeking GAN | |
| Unroll GAN |
Different Structure from the Original GAN
| 题目 | 内容 |
| Conditional GAN | |
| Semi-supervised GAN | |
| InfoGAN | |
| BiGAN | |
| Cycle GAN | |
| Disco GAN | |
| VAE-GAN | |
| LAPGAN | 用了多个GAN可生成高分辨率图像 |
GAN Application
| pix2pix | |
| 题目 | 内容 |
| Image-to-Image Translation with Conditional Adversarial Networks | image2image、paired Image-to-Image Translation |
| High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs |
image2imageHD、paired Image-to-Image Translation |
| CycleGAN | Unpaired Image-to-Image Translation |
| Disco GAN | 侧重分析双向映射，或者说 bijective mapping 的约束：避免 mode collapse 进而提升生成样本质量的 |
| DualGAN | 生成器和判别器都和pix2pix一样。 用了wgan来训练。 |
| 注：最后三篇论文的想法十分相似，几乎可以说是孪生三兄弟 | |
| text2image | |
| 题目 | 内容 |
| 人脸生成 | |
| 题目 | 内容 |
| Face-generator - Generate human faces with neural networks | |
| Beyond Face Rotation: Global and Local Perception GAN for Photorealistic and Identity Preserving Frontal View Synthesis | 根据单一侧脸生成正面逼真人脸 |
| NEURAL FACE | use DCGAN、链接：https://carpedm20.github.io/faces/ |
| 注：DCGAN、WGAN这类都可以生成人脸 | |
| 按生成的图片种类分 | |
| 题目 | 内容 |
| 生成卧室 | DCGAN、WGAN |
| 生成动漫头像 | DCGAN |