Dynamic Attentive Graph Learning for Image Restoration
This repository is for GATIR introduced in the following paper:
Chong Mou, Jian Zhang, Zhuoyuan Wu; Dynamic Attentive Graph Learning for Image Restoration; IEEE International Conference on Computer Vision (ICCV) 2021 [arxiv]
The pre-trained models are available at Google Drive
Requirements
- Python 3.6
- PyTorch >= 1.1.0
- numpy
- skimage
- cv2
Introduction
In this paper, we propose an improved graph attention model for image restoration. Unlike previous non-local image restoration methods, our model can assign an adaptive number of neighbors for each query item and construct long-range correlations based on feature patches. Furthermore, our proposed dynamic attentive graph learning can be easily extended to other computer vision tasks. Extensive experiments demonstrate that our proposed model achieves state-of-the-art performance on wide image restoration tasks: synthetic image denoising, real image denoising, image demosaicing, and compression artifact reduction.
Citation
If you find our work helpful in your resarch or work, please cite the following paper.
@inproceedings{mou2021gatir,
title={Dynamic Attentive Graph Learning for Image Restoration},
author={Chong, Mou and Jian, Zhang and Zhuoyuan, Wu},
booktitle={IEEE International Conference on Computer Vision},
year={2021}
}
![[ICCV2021] Official code for](https://github.com/Uason-Chen/CTR-GCN/raw/main/src/framework.jpg)
148 Dec 16, 2022
859 Dec 22, 2022
22 Dec 17, 2022
303 Dec 31, 2022
69 Dec 15, 2022
17.2k Jan 2, 2023
2.4k Jan 8, 2023
497 Dec 22, 2022
11 Jun 19, 2022
159 Dec 30, 2022
906 Dec 30, 2022
2k Dec 31, 2022
21 Nov 28, 2022
88 Nov 7, 2022
7.4k Jan 1, 2023
3.3k Jan 6, 2023