Report/Docs/2024-10-25/Survey.md

30 lines
852 B
Markdown
Raw Blame History

This file contains ambiguous Unicode characters!

This file contains ambiguous Unicode characters that may be confused with others in your current locale. If your use case is intentional and legitimate, you can safely ignore this warning. Use the Escape button to highlight these characters.

# Diffusion
Introduced by Ho et al. in Denoising Diffusion Probabilistic Models https://arxiv.org/pdf/2006.11239v2
![Alt text](imgs/DiffusionTasks.png)
![img.png](imgs/DiffusionUsages.png)
![img.png](imgs/DiffusionMethods.png)
## 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
扩散模型通过一个特殊的退化过程,逐步地恢复图像,它采用了一个前向马尔可夫链和反向马尔可夫链。在扩散模型中,正向过程涉及一个马尔可夫链,它将数据逐步转化为噪声。
## 3.Papers & Methods
## 4.Networks
## 5.Comparision
## 1.Denoising
## 2.Image Generation
## 3.Image Reconstruction
## 4.Inpainting
## 5.Video Generation