RPD-Diff: Region-Adaptive Physics-Guided Diffusion Model for Visibility Enhancement under Dense and Non-Uniform Haze


Ruicheng Zhang (SUN YAT-SEN UNIVERSITY), Puxin Yan (SUN YAT-SEN UNIVERSITY), Zeyu Zhang (The Australian National University), Yicheng Chang (SUN YAT-SEN UNIVERSITY), Hongyi Chen (SUN YAT-SEN UNIVERSITY), Zhi Jin (SUN YAT-SEN UNIVERSITY)
The 35th British Machine Vision Conference
PDFPosterVideo (Right click to download)

Abstract

Single-image dehazing under dense and non-uniform haze conditions remains challenging due to severe information degradation and spatial heterogeneity. Traditional diffusion-based dehazing methods struggle with insufficient generation conditioning and lack of adaptability to spatially varying haze distributions, which leads to suboptimal restoration. To address these limitations, we propose RPD-Diff, a Region-adaptive Physics-guided Dehazing Diffusion Model for robust visibility enhancement in complex haze scenarios. RPD-Diff introduces a Physics-guided Intermediate State Targeting (PIST) strategy, which leverages physical priors to reformulate the diffusion Markov chain by generation target transitions, mitigating the issue of insufficient conditioning in dense haze scenarios. Additionally, the Haze-Aware Denoising Timestep Predictor (HADTP) dynamically adjusts patch-specific denoising timesteps employing a transmission map cross-attention mechanism, adeptly managing non-uniform haze distributions. Extensive experiments across four real-world datasets demonstrate that RPD-Diff achieves state-of-the-art performance in challenging dense and non-uniform haze scenarios, delivering high-quality, haze-free images with superior detail clarity and color fidelity.

Citation

@inproceedings{Zhang_2025_BMVC,
author    = {Ruicheng Zhang and Puxin Yan and Zeyu Zhang and Yicheng Chang and Hongyi Chen and Zhi Jin},
title     = {RPD-Diff: Region-Adaptive Physics-Guided Diffusion Model for Visibility Enhancement under Dense and Non-Uniform Haze},
booktitle = {36th British Machine Vision Conference 2025, {BMVC} 2025, Sheffield, UK, November 24-27, 2025},
publisher = {BMVA},
year      = {2025},
url       = {https://bmva-archive.org.uk/bmvc/2025/assets/papers/Paper_83/paper.pdf}
}


Copyright © 2025 The British Machine Vision Association and Society for Pattern Recognition
The British Machine Vision Conference is organised by The British Machine Vision Association and Society for Pattern Recognition. The Association is a Company limited by guarantee, No.2543446, and a non-profit-making body, registered in England and Wales as Charity No.1002307 (Registered Office: Dept. of Computer Science, Durham University, South Road, Durham, DH1 3LE, UK).

Imprint | Data Protection