Single Image Rain Streak Removal Using Harris Corner Loss and R-CBAM Network
Fuente:
arXiv
Guardado en:
| Autores principales: | , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912511823970304 |
|---|---|
| author | Si, Jongwook Kim, Sungyoung |
| author_facet | Si, Jongwook Kim, Sungyoung |
| contents | The problem of single-image rain streak removal goes beyond simple noise suppression, requiring the simultaneous preservation of fine structural details and overall visual quality. In this study, we propose a novel image restoration network that effectively constrains the restoration process by introducing a Corner Loss, which prevents the loss of object boundaries and detailed texture information during restoration. Furthermore, we propose a Residual Convolutional Block Attention Module (R-CBAM) Block into the encoder and decoder to dynamically adjust the importance of features in both spatial and channel dimensions, enabling the network to focus more effectively on regions heavily affected by rain streaks. Quantitative evaluations conducted on the Rain100L and Rain100H datasets demonstrate that the proposed method significantly outperforms previous approaches, achieving a PSNR of 33.29 dB on Rain100L and 26.16 dB on Rain100H. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_23185 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Single Image Rain Streak Removal Using Harris Corner Loss and R-CBAM Network Si, Jongwook Kim, Sungyoung Computer Vision and Pattern Recognition Image and Video Processing The problem of single-image rain streak removal goes beyond simple noise suppression, requiring the simultaneous preservation of fine structural details and overall visual quality. In this study, we propose a novel image restoration network that effectively constrains the restoration process by introducing a Corner Loss, which prevents the loss of object boundaries and detailed texture information during restoration. Furthermore, we propose a Residual Convolutional Block Attention Module (R-CBAM) Block into the encoder and decoder to dynamically adjust the importance of features in both spatial and channel dimensions, enabling the network to focus more effectively on regions heavily affected by rain streaks. Quantitative evaluations conducted on the Rain100L and Rain100H datasets demonstrate that the proposed method significantly outperforms previous approaches, achieving a PSNR of 33.29 dB on Rain100L and 26.16 dB on Rain100H. |
| title | Single Image Rain Streak Removal Using Harris Corner Loss and R-CBAM Network |
| topic | Computer Vision and Pattern Recognition Image and Video Processing |
| url | https://arxiv.org/abs/2507.23185 |