39 lines
704 B
Markdown
39 lines
704 B
Markdown
|
# Diffusion
|
|||
|
|
Introduced by Ho et al. in Denoising Diffusion Probabilistic Models https://arxiv.org/pdf/2006.11239v2
|
|||
|
|
|
|||
|
|
## 1.Description
|
|||
|
|
|
|||
|
|
## 2.Background
|
|||
|
|
各式各样的深度生成模型最近都表现出了高质量样本数据模式：生成对抗网络GANs、自回归模型、流和变分自编码器VAE已经合成出了图像和样本
|
|||
|
|
|
|||
|
|
扩散模型(Diffusion Probabilistic model)是一个参数化马尔可夫链
|
|||
|
|
|
|||
|
|
## 3.Papers & Methods
|
|||
|
|
*
|
|||
|
|
*
|
|||
|
|
*
|
|||
|
|
*
|
|||
|
|
## 4.Networks
|
|||
|
|
|
|||
|
|
|
|||
|
|
## 5.Comparision
|
|||
|
|
| Method | Venue | | |
|
|||
|
|
|--|--|--|--|
|
|||
|
|
| | | | |
|
|||
|
|
|
|||
|
|
## 1.Denoising
|
|||
|
|
### 1）Description
|
|||
|
|
|
|||
|
|
### 2）
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
## 2.Image Generation
|
|||
|
|
|
|||
|
|
## 3.Image Reconstruction
|
|||
|
|
|
|||
|
|
## 4.Inpainting
|
|||
|
|
|
|||
|
|
## 5.Video Generation
|