Channel Consistency Prior and Self-Reconstruction Strategy Based Unsupervised Image Deraining
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916660815855616 |
|---|---|
| author | Dong, Guanglu Zheng, Tianheng Cao, Yuanzhouhan Qing, Linbo Ren, Chao |
| author_facet | Dong, Guanglu Zheng, Tianheng Cao, Yuanzhouhan Qing, Linbo Ren, Chao |
| contents | Recently, deep image deraining models based on paired datasets have made a series of remarkable progress. However, they cannot be well applied in real-world applications due to the difficulty of obtaining real paired datasets and the poor generalization performance. In this paper, we propose a novel Channel Consistency Prior and Self-Reconstruction Strategy Based Unsupervised Image Deraining framework, CSUD, to tackle the aforementioned challenges. During training with unpaired data, CSUD is capable of generating high-quality pseudo clean and rainy image pairs which are used to enhance the performance of deraining network. Specifically, to preserve more image background details while transferring rain streaks from rainy images to the unpaired clean images, we propose a novel Channel Consistency Loss (CCLoss) by introducing the Channel Consistency Prior (CCP) of rain streaks into training process, thereby ensuring that the generated pseudo rainy images closely resemble the real ones. Furthermore, we propose a novel Self-Reconstruction (SR) strategy to alleviate the redundant information transfer problem of the generator, further improving the deraining performance and the generalization capability of our method. Extensive experiments on multiple synthetic and real-world datasets demonstrate that the deraining performance of CSUD surpasses other state-of-the-art unsupervised methods and CSUD exhibits superior generalization capability. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_18703 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Channel Consistency Prior and Self-Reconstruction Strategy Based Unsupervised Image Deraining Dong, Guanglu Zheng, Tianheng Cao, Yuanzhouhan Qing, Linbo Ren, Chao Computer Vision and Pattern Recognition Recently, deep image deraining models based on paired datasets have made a series of remarkable progress. However, they cannot be well applied in real-world applications due to the difficulty of obtaining real paired datasets and the poor generalization performance. In this paper, we propose a novel Channel Consistency Prior and Self-Reconstruction Strategy Based Unsupervised Image Deraining framework, CSUD, to tackle the aforementioned challenges. During training with unpaired data, CSUD is capable of generating high-quality pseudo clean and rainy image pairs which are used to enhance the performance of deraining network. Specifically, to preserve more image background details while transferring rain streaks from rainy images to the unpaired clean images, we propose a novel Channel Consistency Loss (CCLoss) by introducing the Channel Consistency Prior (CCP) of rain streaks into training process, thereby ensuring that the generated pseudo rainy images closely resemble the real ones. Furthermore, we propose a novel Self-Reconstruction (SR) strategy to alleviate the redundant information transfer problem of the generator, further improving the deraining performance and the generalization capability of our method. Extensive experiments on multiple synthetic and real-world datasets demonstrate that the deraining performance of CSUD surpasses other state-of-the-art unsupervised methods and CSUD exhibits superior generalization capability. |
| title | Channel Consistency Prior and Self-Reconstruction Strategy Based Unsupervised Image Deraining |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.18703 |