PromptHaze: Prompting Real-world Dehazing via Depth Anything Model
Tian Ye, Sixiang Chen, Haoyu Chen, Wenhao Chai, Jingjing Ren, Zhaohu Xing, Wenxue Li, Lei Zhu
Abstract
Real-world image dehazing remains a challenging task due to the diverse nature of haze degradation and the lack of large-scale paired datasets. Existing methods based on hand-crafted priors or generative priors struggle to recover accurate backgrounds and fine details from dense haze regions. In this work, we propose a novel paradigm, PromptHaze, for real-world image dehazing via the depth prompt from the Depth Anything model. By employing a prompt-by-prompt strategy, our method iteratively updates the depth prompt and progressively restores the background through a dehazing network with controllable dehazing strength. Extensive experiments on widely-used real-world dehazing benchmarks demonstrate the superiority of PromptHaze in recovering authentic backgrounds and fine details from various haze scenes, outperforming state-of-the-art methods across multiple quality metrics.
BibTeX
@article{Ye_Chen_Chen_Chai_Ren_Xing_Li_Zhu_2025, title={PromptHaze: Prompting Real-world Dehazing via Depth Anything Model}, volume={39}, url={https://ojs.aaai.org/index.php/AAAI/article/view/33024}, DOI={10.1609/aaai.v39i9.33024}, abstractNote={Real-world image dehazing remains a challenging task due to the diverse nature of haze degradation and the lack of large-scale paired datasets. Existing methods based on hand-crafted priors or generative priors struggle to recover accurate backgrounds and fine details from dense haze regions. In this work, we propose a novel paradigm, PromptHaze, for real-world image dehazing via the depth prompt from the Depth Anything model. By employing a prompt-by-prompt strategy, our method iteratively updates the depth prompt and progressively restores the background through a dehazing network with controllable dehazing strength. Extensive experiments on widely-used real-world dehazing benchmarks demonstrate the superiority of PromptHaze in recovering authentic backgrounds and fine details from various haze scenes, outperforming state-of-the-art methods across multiple quality metrics.}, number={9}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Ye, Tian and Chen, Sixiang and Chen, Haoyu and Chai, Wenhao and Ren, Jingjing and Xing, Zhaohu and Li, Wenxue and Zhu, Lei}, year={2025}, month={Apr.}, pages={9454-9462} }