DDNM

> 编程语言

Open source

[ICLR 2023 Oral] Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Model

1.3K stars0 likes1 views

Website GitHub

About

[ICLR 2023 Oral] Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Model

Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Model

Paper|️Project Page|

Yinhuai Wang*, Jiwen Yu*, Jian Zhang
Peking University and PCL
*denotes equal contribution

This repository contains the code release for Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Model. DDNM can solve various image restoration tasks without any optimization or training! Yes, in a zero-shot manner.

Supported Applications:

Arbitrary Size
Old Photo Restoration
Super-Resolution
Denoising
Colorization
Inpainting
Deblurring
Compressed Sensing

News

A Colab demo for high-quality results is now avaliable!

Installation

Code

bash

git clone https://github.com/wyhuai/DDNM.git

Environment

bash

pip install numpy torch blobfile tqdm pyYaml pillow    # e.g. torch 1.7.1+cu110.

Pre-Trained Models

To restore human face images, download this model(from SDEdit) and put it into DDNM/exp/logs/celeba/.

https://drive.google.com/file/d/1wSoA5fm_d6JBZk4RZ1SzWLMgev4WqH21/view?usp=share_link

To restore general images, download this model(from guided-diffusion) and put it into DDNM/exp/logs/imagenet/.

bash

wget https://openaipublic.blob.core.windows.net/diffusion/jul-2021/256x256_diffusion_uncond.pt

Quick Start

Run below command to get 4x SR results immediately. The results should be in DDNM/exp/image_samples/demo.

bash

python main.py --ni --simplified --config celeba_hq.yml --path_y celeba_hq --eta 0.85 --deg "sr_averagepooling" --deg_scale 4.0 --sigma_y 0 -i demo

Setting

The detailed sampling command is here:

bash

python main.py --ni --simplified --config {CONFIG}.yml --path_y {PATH_Y} --eta {ETA} --deg {DEGRADATION} --deg_scale {DEGRADATION_SCALE} --sigma_y {SIGMA_Y} -i {IMAGE_FOLDER}

with following options:

We implement TWO versions of DDNM in this repository. One is SVD-based version, which is more precise in solving noisy tasks. Another one is the simplified version, which does not involve SVD and is flexible for users to define their own degradations. Use --simplified to activate the simplified DDNM. Without --simplified will turn to the SVD-based DDNM.
PATH_Y is the folder name of the test dataset, in DDNM/exp/datasets.
ETA is the DDIM hyperparameter. (default: 0.85)
DEGREDATION is the supported tasks including cs_walshhadamard, cs_blockbased, inpainting, denoising, deblur_uni, deblur_gauss, deblur_aniso, sr_averagepooling,sr_bicubic, colorization, mask_color_sr, and user-defined diy.
DEGRADATION_SCALE is the scale of degredation. e.g., --deg sr_bicubic --deg_scale 4 lead to 4xSR.
SIGMA_Y is the noise observed in y.
CONFIG is the name of the config file (see configs/ for a list), including hyperparameters such as batch size and sampling step.
IMAGE_FOLDER is the folder name of the results.

For the config files, e.g., celeba_hq.yml, you may change following properties:

sampling:
    batch_size: 1
    
time_travel:
    T_sampling: 100     # sampling steps
    travel_length: 1    # time-travel parameters l and s, see section 3.3 of the paper.
    travel_repeat: 1    # time-travel parameter r, see section 3.3 of the paper.

Reproduce The Results In The Paper

Quantitative Evaluation

Dataset download link: [Google drive] [Baidu drive]

Download the CelebA testset and put it into DDNM/exp/datasets/celeba/.

Download the ImageNet testset and put it into DDNM/exp/datasets/imagenet/ and replace the file DDNM/exp/imagenet_val_1k.txt.

Run the following command. You may increase the batch_size to accelerate evaluation.

sh evaluation.sh

High-Quality Results

You can try this Colab demo for High-Quality results. Note that the High-Quality results presented in the front figure are mostly generated by applying DDNM to the models in RePaint.

Real-World Applications

Demo: Real-World Super-Resolution.

Run the following command

bash

python main.py --ni --simplified --config celeba_hq.yml --path_y solvay --eta 0.85 --deg "sr_averagepooling" --deg_scale 4.0 --sigma_y 0.1 -i demo

Demo: Old Photo Restoration.

Run the following command

bash

python main.py --ni --simplified --config oldphoto.yml --path_y oldphoto --eta 0.85 --deg "mask_color_sr" --deg_scale 2.0 --sigma_y 0.02 -i demo

Try your own photos.

You may use DDNM to restore your own degraded images. DDNM provides full flexibility for you to define the degradation operator and the noise level. Note that these definitions are critical for a good results. You may reference the following guidance.

If you are using CelebA pretrained models, try the tool in GFPGAN to crop and align your photo.
If there are local artifacts on your photo, try the tool in LaMa to draw a mask to cover them, and save this mask to DDNM/exp/inp_masks/mask.png. Then run DDNM/exp/inp_masks/get_mask.py to generate mask.npy.
If your photo is faded, you need a grayscale operator as part of the degradation.
If your photo is blur, you need a downsampler operator as part of the degradation. Also, you need to set a proper SR scale --deg_scale.
If your photo suffers global artifacts, e.g., jpeg-like artifacts or unkown noise, you need to set a proper sigma_y to remove these artifacts.
Search args.deg =='diy' in DDNM/guided_diffusion/diffusion.py and change the definition of $\mathbf{A}$ correspondingly. Then run

bash

python main.py --ni --simplified --config celeba_hq.yml --path_y {YOUR_OWN_PATH} --eta 0.85 --deg "diy" --deg_scale {YOUR_OWN_SCALE} --sigma_y {YOUR_OWN_LEVEL} -i diy

DDNM for Arbitrary Size

Above we show an example of using DDNM to SR a 64x256 input image into a 256x1024 result. The theory details can be found in this paper, section 3.3.

We implement the Mask-Shift Restoration in the folder hq_demo, based on RePaint. You can try this Colab demo.

Or, you can try this function on your own device, you need to download the pre-trained models:

bash

wget https://openaipublic.blob.core.windows.net/diffusion/jul-2021/256x256_classifier.pt
wget https://openaipublic.blob.core.windows.net/diffusion/jul-2021/256x256_diffusion.pt

and put it to hq_demo/data/pretrained. Then run

bash

cd hq_demo
sh evaluation.sh

This script contains SR results up to 2K resolution. It may take hours to finish some demos in this script. Setting a smaller sampling step or time-travel parameters in hq_demo/confs/inet256.yml can speed up, but may compromise the generative quality.

Applying DDNM to Your Own Diffusion Model

It is very easy to implement a basic DDNM on your own diffusion model! You may reference the following:

Copy these operator implementations to the core diffusion sampling file, then define your task type, e.g., set IR_mode="super resolution".

…

Find the variant $\mathbf{x}_{0|t}$ in the target codes, and use the result of this function to modify the sampling of $\mathbf{x}_{t-1}$. Your may need to provide the input degraded image $\mathbf{y}$ and the corresponding noise level $\sigma_\mathbf{y}$.

python

# Core Implementation of DDNM+, simplified denoising solution (Section 3.3).
# For more accurate denoising, please refer to the paper (Appendix I) and the source code.

def ddnm_plus_core(x0t, y, sigma_y=0, sigma_t, a_t):

    #Eq 19
    if sigma_t >= a_t*sigma_y: 
        lambda_t = 1
        gamma_t = sigma_t**2 - (a_t*lambda_t*sigma_y)**2
    else:
        lambda_t = sigma_t/(a_t*sigma_y)
        gamma_t = 0
        
    #Eq 17    
    x0t= x0t + lambda_t*Ap(y - A(x0t))
    
    return x0t, gamma_t

Actually, this repository contains the above simplified implementation: try search arg.simplified in DDNM/guided_diffusion/diffusion.py for related codes.

References

If you find this repository useful for your research, please cite the following work.

@article{wang2022zero,
  title={Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Model},
  author={Wang, Yinhuai and Yu, Jiwen and Zhang, Jian},
  journal={The Eleventh International Conference on Learning Representations},
  year={2023}
}

This implementation is based on / inspired by: