CoA: Towards Real Image Dehazing via Compression-and-Adaptation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909571225747456 |
|---|---|
| author | Ma, Long Feng, Yuxin Zhang, Yan Liu, Jinyuan Wang, Weimin Chen, Guang-Yong Xu, Chengpei Su, Zhuo |
| author_facet | Ma, Long Feng, Yuxin Zhang, Yan Liu, Jinyuan Wang, Weimin Chen, Guang-Yong Xu, Chengpei Su, Zhuo |
| contents | Learning-based image dehazing algorithms have shown remarkable success in synthetic domains. However, real image dehazing is still in suspense due to computational resource constraints and the diversity of real-world scenes. Therefore, there is an urgent need for an algorithm that excels in both efficiency and adaptability to address real image dehazing effectively. This work proposes a Compression-and-Adaptation (CoA) computational flow to tackle these challenges from a divide-and-conquer perspective. First, model compression is performed in the synthetic domain to develop a compact dehazing parameter space, satisfying efficiency demands. Then, a bilevel adaptation in the real domain is introduced to be fearless in unknown real environments by aggregating the synthetic dehazing capabilities during the learning process. Leveraging a succinct design free from additional constraints, our CoA exhibits domain-irrelevant stability and model-agnostic flexibility, effectively bridging the model chasm between synthetic and real domains to further improve its practical utility. Extensive evaluations and analyses underscore the approach's superiority and effectiveness. The code is publicly available at https://github.com/fyxnl/COA. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_05590 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | CoA: Towards Real Image Dehazing via Compression-and-Adaptation Ma, Long Feng, Yuxin Zhang, Yan Liu, Jinyuan Wang, Weimin Chen, Guang-Yong Xu, Chengpei Su, Zhuo Computer Vision and Pattern Recognition Learning-based image dehazing algorithms have shown remarkable success in synthetic domains. However, real image dehazing is still in suspense due to computational resource constraints and the diversity of real-world scenes. Therefore, there is an urgent need for an algorithm that excels in both efficiency and adaptability to address real image dehazing effectively. This work proposes a Compression-and-Adaptation (CoA) computational flow to tackle these challenges from a divide-and-conquer perspective. First, model compression is performed in the synthetic domain to develop a compact dehazing parameter space, satisfying efficiency demands. Then, a bilevel adaptation in the real domain is introduced to be fearless in unknown real environments by aggregating the synthetic dehazing capabilities during the learning process. Leveraging a succinct design free from additional constraints, our CoA exhibits domain-irrelevant stability and model-agnostic flexibility, effectively bridging the model chasm between synthetic and real domains to further improve its practical utility. Extensive evaluations and analyses underscore the approach's superiority and effectiveness. The code is publicly available at https://github.com/fyxnl/COA. |
| title | CoA: Towards Real Image Dehazing via Compression-and-Adaptation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2504.05590 |