Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Zhang, Ruicheng, Yan, Puxin, Zhang, Zeyu, Chang, Yicheng, Chen, Hongyi, Jin, Zhi
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2508.16956
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866916913700929536
author Zhang, Ruicheng
Yan, Puxin
Zhang, Zeyu
Chang, Yicheng
Chen, Hongyi
Jin, Zhi
author_facet Zhang, Ruicheng
Yan, Puxin
Zhang, Zeyu
Chang, Yicheng
Chen, Hongyi
Jin, Zhi
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2508_16956
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle RPD-Diff: Region-Adaptive Physics-Guided Diffusion Model for Visibility Enhancement under Dense and Non-Uniform Haze
Zhang, Ruicheng
Yan, Puxin
Zhang, Zeyu
Chang, Yicheng
Chen, Hongyi
Jin, Zhi
Computer Vision and Pattern Recognition
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.
title RPD-Diff: Region-Adaptive Physics-Guided Diffusion Model for Visibility Enhancement under Dense and Non-Uniform Haze
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2508.16956