Towards Real-World Adverse Weather Image Restoration: Enhancing Clearness and Semantics with Vision-Language Models
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866910588513288192 |
|---|---|
| author | Xu, Jiaqi Wu, Mengyang Hu, Xiaowei Fu, Chi-Wing Dou, Qi Heng, Pheng-Ann |
| author_facet | Xu, Jiaqi Wu, Mengyang Hu, Xiaowei Fu, Chi-Wing Dou, Qi Heng, Pheng-Ann |
| contents | This paper addresses the limitations of adverse weather image restoration approaches trained on synthetic data when applied to real-world scenarios. We formulate a semi-supervised learning framework employing vision-language models to enhance restoration performance across diverse adverse weather conditions in real-world settings. Our approach involves assessing image clearness and providing semantics using vision-language models on real data, serving as supervision signals for training restoration models. For clearness enhancement, we use real-world data, utilizing a dual-step strategy with pseudo-labels assessed by vision-language models and weather prompt learning. For semantic enhancement, we integrate real-world data by adjusting weather conditions in vision-language model descriptions while preserving semantic meaning. Additionally, we introduce an effective training strategy to bootstrap restoration performance. Our approach achieves superior results in real-world adverse weather image restoration, demonstrated through qualitative and quantitative comparisons with state-of-the-art works. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_02101 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Towards Real-World Adverse Weather Image Restoration: Enhancing Clearness and Semantics with Vision-Language Models Xu, Jiaqi Wu, Mengyang Hu, Xiaowei Fu, Chi-Wing Dou, Qi Heng, Pheng-Ann Computer Vision and Pattern Recognition Multimedia This paper addresses the limitations of adverse weather image restoration approaches trained on synthetic data when applied to real-world scenarios. We formulate a semi-supervised learning framework employing vision-language models to enhance restoration performance across diverse adverse weather conditions in real-world settings. Our approach involves assessing image clearness and providing semantics using vision-language models on real data, serving as supervision signals for training restoration models. For clearness enhancement, we use real-world data, utilizing a dual-step strategy with pseudo-labels assessed by vision-language models and weather prompt learning. For semantic enhancement, we integrate real-world data by adjusting weather conditions in vision-language model descriptions while preserving semantic meaning. Additionally, we introduce an effective training strategy to bootstrap restoration performance. Our approach achieves superior results in real-world adverse weather image restoration, demonstrated through qualitative and quantitative comparisons with state-of-the-art works. |
| title | Towards Real-World Adverse Weather Image Restoration: Enhancing Clearness and Semantics with Vision-Language Models |
| topic | Computer Vision and Pattern Recognition Multimedia |
| url | https://arxiv.org/abs/2409.02101 |