Awesome
IDR: Self-Supervised Image Denoising via Iterative Data Refinement
Yi Zhang<sup>1</sup>, Dasong Li<sup>1</sup>, Ka Lung Law<sup>2</sup>, Xiaogang Wang<sup>1</sup>, Hongwei Qin<sup>2</sup>, Hongsheng Li<sup>1</sup><br> <sup>1</sup>CUHK-SenseTime Joint Lab, <sup>2</sup>SenseTime Research
This repository is the official PyTorch implementation of IDR. It also includes some personal implementations of well-known unsupervised image denoising methods (N2N, etc).
Update
- 2023.08.01: We release the sensenoise dataset v4, which contains both Raw images, sRGB images and meta information (e.g. lens shading, ccm).
SenseNoise dataset
V4 Downloads:
V3 Downloads: OneDrive | Baidu Netdisk
Thanks to the advice from the anonymous reviewers, we are still working on improving the quality of the dataset.
Training
Slurm Training. Find the config name in configs/synthetic_config.py.
sh run_slurm.sh -n config_name
Example of training IDR for Gaussian denoising:
sh run_slurm.sh -n idr-g
Testing
The code has been tested with the following environment:
pytorch == 1.5.0
bm3d == 3.0.7
scipy == 1.4.1
- Prepare the datasets. (kodak | BSDS300 | BSD68)
- Download the pretrained models and put them into the checkpoint folder.
- Modify the data root path and noise type (gaussian | gaussian_gray | line | binomial | impulse | pattern).
python -u test.py --root your_data_root --ntype gaussian
Citation
@inproceedings{zhang2021IDR,
title={IDR: Self-Supervised Image Denoising via Iterative Data Refinement},
author={Zhang, Yi and Li, Dasong and Law, Ka Lung and Wang, Xiaogang and Qin, Hongwei and Li, Hongsheng},
booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
year={2022}
}
Contact
Feel free to contact zhangyi@link.cuhk.edu.hk if you have any questions.