URDS: A Dual-Branch ViTs and CNNs Framework for Unpaired Raindrop and Rain Streak Removal
Rain streaks and raindrops severely degrade image quality and adversely affect vision-based systems in outdoor environments. Removing such rain artifacts is critical for reliable visual recognition. Although supervised deraining methods achieve strong performance, unpaired data remains a major chall...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/11082152/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849714377701195776 |
|---|---|
| author | Nianyun Liu Kebin Sha Junwei Yan Xinxi Xie |
| author_facet | Nianyun Liu Kebin Sha Junwei Yan Xinxi Xie |
| author_sort | Nianyun Liu |
| collection | DOAJ |
| description | Rain streaks and raindrops severely degrade image quality and adversely affect vision-based systems in outdoor environments. Removing such rain artifacts is critical for reliable visual recognition. Although supervised deraining methods achieve strong performance, unpaired data remains a major challenge due to the absence of pixel-level supervision. In this study, we propose a novel dual-branch GAN-based framework for unpaired rain detection and removal. For rain detection, we introduce a rain perception block that integrates channel sparse transformer and spatial gated convolution, enhancing feature extraction across channel and spatial dimensions and to generate precise rain masks. For rain removal, we design a rain-attentive block that leverages the detected rain mask as guidance, enabling high-performance deraining in an unsupervised manner. Extensive experiments on benchmark datasets demonstrate that our method achieves state-of-the-art performance in unsupervised rain removal. Specifically, it outperforms existing unsupervised approaches on the RainDS dataset. On Rain200L, Rain200H, and RainDrop, it achieves PSNR/SSIM scores of 34.78 dB/0.9637, 24.85 dB/0.8017, and 29.00 dB/0.9095, respectively, with average improvements of 1.50 dB in PSNR and 0.03 in SSIM. Comprehensive ablation studies further validate the critical contributions of both the Rain Perception Block (RPB) and Rain Attentive Block (RAB) modules to the overall system performance. |
| format | Article |
| id | doaj-art-6aebcf3d2a52411490a4e745c368a43d |
| institution | DOAJ |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-6aebcf3d2a52411490a4e745c368a43d2025-08-20T03:13:43ZengIEEEIEEE Access2169-35362025-01-011312548512549810.1109/ACCESS.2025.358850811082152URDS: A Dual-Branch ViTs and CNNs Framework for Unpaired Raindrop and Rain Streak RemovalNianyun Liu0Kebin Sha1Junwei Yan2https://orcid.org/0000-0003-4170-981XXinxi Xie3https://orcid.org/0009-0009-9454-1265School of Business, Jianghan University, Wuhan, ChinaShanghai Harbor Digital Technology Company Ltd., Shanghai, ChinaSchool of Information Engineering, Wuhan University of Technology, Wuhan, ChinaSchool of Information Engineering, Wuhan University of Technology, Wuhan, ChinaRain streaks and raindrops severely degrade image quality and adversely affect vision-based systems in outdoor environments. Removing such rain artifacts is critical for reliable visual recognition. Although supervised deraining methods achieve strong performance, unpaired data remains a major challenge due to the absence of pixel-level supervision. In this study, we propose a novel dual-branch GAN-based framework for unpaired rain detection and removal. For rain detection, we introduce a rain perception block that integrates channel sparse transformer and spatial gated convolution, enhancing feature extraction across channel and spatial dimensions and to generate precise rain masks. For rain removal, we design a rain-attentive block that leverages the detected rain mask as guidance, enabling high-performance deraining in an unsupervised manner. Extensive experiments on benchmark datasets demonstrate that our method achieves state-of-the-art performance in unsupervised rain removal. Specifically, it outperforms existing unsupervised approaches on the RainDS dataset. On Rain200L, Rain200H, and RainDrop, it achieves PSNR/SSIM scores of 34.78 dB/0.9637, 24.85 dB/0.8017, and 29.00 dB/0.9095, respectively, with average improvements of 1.50 dB in PSNR and 0.03 in SSIM. Comprehensive ablation studies further validate the critical contributions of both the Rain Perception Block (RPB) and Rain Attentive Block (RAB) modules to the overall system performance.https://ieeexplore.ieee.org/document/11082152/Image derainingtransformerdeep learningraindrop removalattention mechanism |
| spellingShingle | Nianyun Liu Kebin Sha Junwei Yan Xinxi Xie URDS: A Dual-Branch ViTs and CNNs Framework for Unpaired Raindrop and Rain Streak Removal IEEE Access Image deraining transformer deep learning raindrop removal attention mechanism |
| title | URDS: A Dual-Branch ViTs and CNNs Framework for Unpaired Raindrop and Rain Streak Removal |
| title_full | URDS: A Dual-Branch ViTs and CNNs Framework for Unpaired Raindrop and Rain Streak Removal |
| title_fullStr | URDS: A Dual-Branch ViTs and CNNs Framework for Unpaired Raindrop and Rain Streak Removal |
| title_full_unstemmed | URDS: A Dual-Branch ViTs and CNNs Framework for Unpaired Raindrop and Rain Streak Removal |
| title_short | URDS: A Dual-Branch ViTs and CNNs Framework for Unpaired Raindrop and Rain Streak Removal |
| title_sort | urds a dual branch vits and cnns framework for unpaired raindrop and rain streak removal |
| topic | Image deraining transformer deep learning raindrop removal attention mechanism |
| url | https://ieeexplore.ieee.org/document/11082152/ |
| work_keys_str_mv | AT nianyunliu urdsadualbranchvitsandcnnsframeworkforunpairedraindropandrainstreakremoval AT kebinsha urdsadualbranchvitsandcnnsframeworkforunpairedraindropandrainstreakremoval AT junweiyan urdsadualbranchvitsandcnnsframeworkforunpairedraindropandrainstreakremoval AT xinxixie urdsadualbranchvitsandcnnsframeworkforunpairedraindropandrainstreakremoval |