Awesome
Residual Denoising Diffusion Models
paper|arxiv|youtube|blog|中文论文(ao9l)|中文视频|中文博客
This repository is the official implementation of Residual Denoising Diffusion Models.
<p align="center"> <a href="https://cvpr.thecvf.com/virtual/2024/poster/31373" target="_blank"> <img width="800" height="400" img align="center" alt="RDDM" src="https://github.com/nachifur/RDDM/blob/main/poster/Jiawei_9969.png" /> </a> </p>Requirements
To install requirements:
conda env create -f install.yaml
Dataset
Training
To train RDDM, run this command:
cd experiments/xxxx
python train.py
or
accelerate launch train.py
Evaluation
To evaluate image generation, run:
cd eval/image_generation_eval/
python fid_and_inception_score.py path_of_gen_img
For image restoration, MATLAB evaluation codes in ./eval
.
Pre-trained Models
Two unets (deresidual+denoising) for partially path-independent generation process
Results
See Table 3 in main paper.
For image restoration:
For image generation (on the CelebA dataset):
We can convert a pre-trained DDIM to RDDM by coefficient transformation (see 1_Image_Generation_convert_pretrained_DDIM_to_RDDM).
Citation
If you find our work useful in your research, please consider citing:
@InProceedings{Liu_2024_CVPR,
author = {Liu, Jiawei and Wang, Qiang and Fan, Huijie and Wang, Yinong and Tang, Yandong and Qu, Liangqiong},
title = {Residual Denoising Diffusion Models},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2024},
pages = {2773-2783}
}
Contact
Please contact Liangqiong Qu (https://liangqiong.github.io/) or Jiawei Liu (liujiawei18@mails.ucas.ac.cn) if there is any question.