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 } 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:this https URL.
View on arXiv@article{wang2025_2505.14010,
title={ UHD Image Dehazing via anDehazeFormer with Atmospheric-aware KV Cache },
author={ Pu Wang and Pengwen Dai and Chen Wu and Yeying Jin and Dianjie Lu and Guijuan Zhang and Youshan Zhang and Zhuoran Zheng },
journal={arXiv preprint arXiv:2505.14010},
year={ 2025 }
}