/DMPlug

This is the official implementation of "DMPlug: A Plug-in Method for Solving Inverse Problems with Diffusion Models".

Primary LanguagePython

DMPlug: A Plug-in Method for Solving Inverse Problems with Diffusion Models

This is the official implementation of "DMPlug: A Plug-in Method for Solving Inverse Problems with Diffusion Models". You can find our paper via arXiv.

Abstract

In this paper, we advocate viewing the reverse process in DMs as a function and propose a novel plug-in method for solving IPs using pretrained DMs, dubbed DMPlug. DMPlug addresses the issues of manifold feasibility and measurement feasibility in a principled manner, and also shows great potential for being robust to unknown types and levels of noise. Through extensive experiments across various IP tasks, including two linear and three nonlinear IPs, we demonstrate that DMPlug consistently outperforms state-of-the-art methods, often by large margins especially for nonlinear IPs (typically 3-6dB in terms of PSNR).

title

Getting started

1) Clone the repository

git clone https://github.com/sun-umn/DMPlug.git

cd DMPlug

2) Download pretrained checkpoint

From the link, download the checkpoint "celebahq_p2.pt" and paste it to ./models/;

From the link, download the checkpoint "ffhq_10m.pt" and paste it to ./models/;

From the link, download the checkpoint "lsun_bedroom.pt" and paste it to ./models/.

mkdir models
mv {DOWNLOAD_DIR}/celebahq_p2.pt ./models/
mv {DOWNLOAD_DIR}/ffqh_10m.pt ./models/
mv {DOWNLOAD_DIR}/lsun_bedroom.pt ./models/

{DOWNLOAD_DIR} is the directory that you downloaded checkpoint to.

3) Set environment

We use the external codes for motion-blurring and non-linear deblurring.

git clone https://github.com/VinAIResearch/blur-kernel-space-exploring bkse

git clone https://github.com/LeviBorodenko/motionblur motionblur

From the link, download the checkpoint "GOPRO_wVAE.pth" and paste it to ./experiments/pretrained/.

mv {DOWNLOAD_DIR}/GOPRO_wVAE.pt ./experiments/pretrained/

{DOWNLOAD_DIR} is the directory that you downloaded checkpoint to.

Install dependencies

conda env create -f environment.yml
conda activate dmplug

Inference

# Superresolution, inpainting, nonlinear deblurring
python sr_inp_nonlinear.py --task 'super_resolution'
python sr_inp_nonlinear.py --task 'inpainting'
python sr_inp_nonlinear.py --task 'nonlinear_deblur'

# BID
python bid.py --kernel 'motion'
python bid.py --kernel 'gaussian'

# BID with turbulence
python turbulence.py

References

This repo is developed based on DPS and BlindDPS, especially for forward operations. Please also consider citing them if you use this repo.

Citation

If you find our work interesting, please consider citing

@misc{wang_dmplug_2024,
	title = {{DMPlug}: {A} {Plug}-in {Method} for {Solving} {Inverse} {Problems} with {Diffusion} {Models}},
	shorttitle = {{DMPlug}},
	url = {http://arxiv.org/abs/2405.16749},
	doi = {10.48550/arXiv.2405.16749},
	urldate = {2024-06-03},
	publisher = {arXiv},
	author = {Wang, Hengkang and Zhang, Xu and Li, Taihui and Wan, Yuxiang and Chen, Tiancong and Sun, Ju},
	month = may,
	year = {2024},
	note = {arXiv:2405.16749 [cs]},
	keywords = {Computer Science - Computer Vision and Pattern Recognition, Computer Science - Machine Learning},
}

Contact