Underwater Image Enhancement via Dehazing and Color Restoration
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866915272032518144 |
|---|---|
| author | Wu, Chengqin Yu, Shuai Luo, Tuyan Rao, Qiuhua Hu, Qingson Xu, Jingxiang Zhang, Lijun |
| author_facet | Wu, Chengqin Yu, Shuai Luo, Tuyan Rao, Qiuhua Hu, Qingson Xu, Jingxiang Zhang, Lijun |
| contents | Underwater visual imaging is crucial for marine engineering, but it suffers from low contrast, blurriness, and color degradation, which hinders downstream analysis. Existing underwater image enhancement methods often treat the haze and color cast as a unified degradation process, neglecting their inherent independence while overlooking their synergistic relationship. To overcome this limitation, we propose a Vision Transformer (ViT)-based network (referred to as WaterFormer) to improve underwater image quality. WaterFormer contains three major components: a dehazing block (DehazeFormer Block) to capture the self-correlated haze features and extract deep-level features, a Color Restoration Block (CRB) to capture self-correlated color cast features, and a Channel Fusion Block (CFB) that dynamically integrates these decoupled features to achieve comprehensive enhancement. To ensure authenticity, a soft reconstruction layer based on the underwater imaging physics model is included. Further, a Chromatic Consistency Loss and Sobel Color Loss are designed to respectively preserve color fidelity and enhance structural details during network training. Comprehensive experimental results demonstrate that WaterFormer outperforms other state-of-the-art methods in enhancing underwater images. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_09779 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Underwater Image Enhancement via Dehazing and Color Restoration Wu, Chengqin Yu, Shuai Luo, Tuyan Rao, Qiuhua Hu, Qingson Xu, Jingxiang Zhang, Lijun Computer Vision and Pattern Recognition Image and Video Processing Underwater visual imaging is crucial for marine engineering, but it suffers from low contrast, blurriness, and color degradation, which hinders downstream analysis. Existing underwater image enhancement methods often treat the haze and color cast as a unified degradation process, neglecting their inherent independence while overlooking their synergistic relationship. To overcome this limitation, we propose a Vision Transformer (ViT)-based network (referred to as WaterFormer) to improve underwater image quality. WaterFormer contains three major components: a dehazing block (DehazeFormer Block) to capture the self-correlated haze features and extract deep-level features, a Color Restoration Block (CRB) to capture self-correlated color cast features, and a Channel Fusion Block (CFB) that dynamically integrates these decoupled features to achieve comprehensive enhancement. To ensure authenticity, a soft reconstruction layer based on the underwater imaging physics model is included. Further, a Chromatic Consistency Loss and Sobel Color Loss are designed to respectively preserve color fidelity and enhance structural details during network training. Comprehensive experimental results demonstrate that WaterFormer outperforms other state-of-the-art methods in enhancing underwater images. |
| title | Underwater Image Enhancement via Dehazing and Color Restoration |
| topic | Computer Vision and Pattern Recognition Image and Video Processing |
| url | https://arxiv.org/abs/2409.09779 |