UHD Image Dehazing via anDehazeFormer with Atmospheric-aware KV Cache
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912383106023424 |
|---|---|
| author | Wang, Pu Dai, Pengwen Wu, Chen Jin, Yeying Lu, Dianjie Zhang, Guijuan Zhang, Youshan Zheng, Zhuoran |
| author_facet | Wang, Pu Dai, Pengwen Wu, Chen Jin, Yeying Lu, Dianjie Zhang, Guijuan Zhang, Youshan Zheng, Zhuoran |
| contents | In this paper, we propose an efficient visual transformer framework for ultra-high-definition (UHD) image dehazing that addresses the key challenges of slow training speed and high memory consumption for existing methods. Our approach introduces two key innovations: 1) an \textbf{a}daptive \textbf{n}ormalization mechanism inspired by the nGPT architecture that enables ultra-fast and stable training with a network with a restricted range of parameter expressions; and 2) we devise an atmospheric scattering-aware KV caching mechanism that dynamically optimizes feature preservation based on the physical haze formation model. The proposed architecture improves the training convergence speed by \textbf{5 $\times$} while reducing memory overhead, enabling real-time processing of 50 high-resolution images per second on an RTX4090 GPU. Experimental results show that our approach maintains state-of-the-art dehazing quality while significantly improving computational efficiency for 4K/8K image restoration tasks. Furthermore, we provide a new dehazing image interpretable method with the help of an integrated gradient attribution map. Our code can be found here: https://anonymous.4open.science/r/anDehazeFormer-632E/README.md. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_14010 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | UHD Image Dehazing via anDehazeFormer with Atmospheric-aware KV Cache Wang, Pu Dai, Pengwen Wu, Chen Jin, Yeying Lu, Dianjie Zhang, Guijuan Zhang, Youshan Zheng, Zhuoran Computer Vision and Pattern Recognition In this paper, we propose an efficient visual transformer framework for ultra-high-definition (UHD) image dehazing that addresses the key challenges of slow training speed and high memory consumption for existing methods. Our approach introduces two key innovations: 1) an \textbf{a}daptive \textbf{n}ormalization mechanism inspired by the nGPT architecture that enables ultra-fast and stable training with a network with a restricted range of parameter expressions; and 2) we devise an atmospheric scattering-aware KV caching mechanism that dynamically optimizes feature preservation based on the physical haze formation model. The proposed architecture improves the training convergence speed by \textbf{5 $\times$} while reducing memory overhead, enabling real-time processing of 50 high-resolution images per second on an RTX4090 GPU. Experimental results show that our approach maintains state-of-the-art dehazing quality while significantly improving computational efficiency for 4K/8K image restoration tasks. Furthermore, we provide a new dehazing image interpretable method with the help of an integrated gradient attribution map. Our code can be found here: https://anonymous.4open.science/r/anDehazeFormer-632E/README.md. |
| title | UHD Image Dehazing via anDehazeFormer with Atmospheric-aware KV Cache |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2505.14010 |