针对浓密不均雾霾，提出自适应物理引导的扩散模型，提升去雾质量。
RPD-Diff: Region-Adaptive Physics-Guided Diffusion Model for Visibility Enhancement under Dense and Non-Uniform Haze
- 引入物理先验重构扩散过程，增强生成条件。
- 动态调整分块去噪步数，适应非均匀雾霾分布。
- 在四个真实数据集上表现领先，细节清晰、色彩保真。
浓密且不均匀的雾霾下单图像去雾仍具挑战，因信息严重退化与空间异质性。传统基于扩散的去雾方法在生成条件不足及对空间变化雾霾分布适应性差方面表现不佳，导致恢复效果不理想。为此，本文提出RPD-Diff：一种区域自适应物理引导的去雾扩散模型，用于复杂雾霾场景下的鲁棒能见度增强。该模型引入物理引导的中间状态目标策略（PIST），利用物理先验重构扩散马尔可夫链，通过生成目标转移缓解浓雾场景中条件不足问题。同时，设计雾霾感知去噪时间步预测器（HADTP），采用透射图交叉注意力机制动态调整分块去噪步数，有效应对非均匀雾霾分布。在四个真实世界数据集上的大量实验表明，RPD-Diff在挑战性的浓密非均匀雾霾场景中达到最先进性能，生成高质量无雾图像，具有更优的细节清晰度与色彩保真度。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。