PASDiff联合增强低光人脸图像，兼顾光照自然与细节清晰。
PASDiff: Physics-Aware Semantic Guidance for Joint Real-World Low-Light Face Enhancement and Restoration
- 引入物理感知的光照约束与面部结构注入机制
- 在700张真实低光人脸图像上显著提升保真度与一致性
- 适合需要高保真人脸修复的视觉应用
真实场景低光照下的人脸图像常面临光照不足、模糊、噪声和可见度低等多重退化问题。现有级联方法易积累误差，通用联合模型缺乏显式人脸先验，难以恢复清晰结构。本文提出PASDiff，一种无需训练的物理感知语义扩散框架。为实现合理的光照与色彩分布，利用逆强度加权和Retinex理论引入光度约束，可靠恢复可见性与自然色度。为精准重建面部细节，提出无风格结构注入（SASI），从现成面部先验中提取结构并过滤其固有光度偏见，无缝融合身份特征与物理约束。此外，构建了包含700张复杂退化人脸的真实世界基准数据集WildDark-Face。大量实验表明，PASDiff在自然光照、色彩恢复与身份一致性间取得更优平衡。代码与数据集将开源于https://github.com/IVIPLab/PASDiff。
原文摘要 · Abstract (English)
Face images captured in real-world low light suffer multiple degradations-low illumination, blur, noise, and low visibility, etc. Existing cascaded solutions often suffer from severe error accumulation, while generic joint models lack explicit facial priors and struggle to resolve clear face structures. In this paper, we propose PASDiff, a Physics-Aware Semantic Diffusion with a training-free manner. To achieve a plausible illumination and color distribution, we leverage inverse intensity weighting and Retinex theory to introduce photometric constraints, thereby reliably recovering visibility and natural chromaticity. To faithfully reconstruct facial details, our Style-Agnostic Structural Injection (SASI) extracts structures from an off-the-shelf facial prior while filtering out its intrinsic photometric biases, seamlessly harmonizing identity features with physical constraints. Furthermore, we construct WildDark-Face, a real-world benchmark of 700 low-light facial images with complex degradations. Extensive experiments demonstrate that PASDiff significantly outperforms existing methods, achieving a superior balance among natural illumination, color recovery, and identity consistency. Code and dataset will be available at https://github.com/IVIPLab/PASDiff.
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。