Memory augment is All You Need for image restoration
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908502455222272 |
|---|---|
| author | Zhang, Xiao Feng Gu, Chao Chen Zhu, Shan Ying |
| author_facet | Zhang, Xiao Feng Gu, Chao Chen Zhu, Shan Ying |
| contents | Image restoration is a low-level vision task, most CNN methods are designed as a black box, lacking transparency and internal aesthetics. Although some methods combining traditional optimization algorithms with DNNs have been proposed, they all have some limitations. In this paper, we propose a three-granularity memory layer and contrast learning named MemoryNet, specifically, dividing the samples into positive, negative, and actual three samples for contrastive learning, where the memory layer is able to preserve the deep features of the image and the contrastive learning converges the learned features to balance. Experiments on Derain/Deshadow/Deblur task demonstrate that these methods are effective in improving restoration performance. In addition, this paper's model obtains significant PSNR, SSIM gain on three datasets with different degradation types, which is a strong proof that the recovered images are perceptually realistic. The source code of MemoryNet can be obtained from https://github.com/zhangbaijin/MemoryNet |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2309_01377 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Memory augment is All You Need for image restoration Zhang, Xiao Feng Gu, Chao Chen Zhu, Shan Ying Computer Vision and Pattern Recognition Artificial Intelligence Image restoration is a low-level vision task, most CNN methods are designed as a black box, lacking transparency and internal aesthetics. Although some methods combining traditional optimization algorithms with DNNs have been proposed, they all have some limitations. In this paper, we propose a three-granularity memory layer and contrast learning named MemoryNet, specifically, dividing the samples into positive, negative, and actual three samples for contrastive learning, where the memory layer is able to preserve the deep features of the image and the contrastive learning converges the learned features to balance. Experiments on Derain/Deshadow/Deblur task demonstrate that these methods are effective in improving restoration performance. In addition, this paper's model obtains significant PSNR, SSIM gain on three datasets with different degradation types, which is a strong proof that the recovered images are perceptually realistic. The source code of MemoryNet can be obtained from https://github.com/zhangbaijin/MemoryNet |
| title | Memory augment is All You Need for image restoration |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2309.01377 |