提出物理对齐的阴影去除方法，提升复杂光照下的去影效果。
PhaSR: Generalized Image Shadow Removal with Physically Aligned Priors
- 通过物理对齐归一化与几何语义注意力，解耦光照与反射特性。
- 在单光源到多光源环境下均表现良好，优于传统方法。
- 适合需要跨光照场景泛化的图像修复任务使用。
在多样光照条件下进行阴影去除，需将光照与固有反照率分离，但当物理先验未正确对齐时挑战加剧。本文提出PhaSR（物理对齐阴影去除），通过双层级先验对齐实现从单光源阴影到多源环境光的鲁棒性能。首先，物理对齐归一化（PAN）采用灰世界归一化、对数域Retinex分解与动态范围重组，实现闭式光照校正，抑制色偏。其次，几何-语义校正注意力（GSRA）将差分注意力扩展至跨模态对齐，融合深度推导几何与DINO-v2语义嵌入，解决不同光照下的模态冲突。实验表明，该方法在阴影去除上具有竞争力，计算复杂度更低，且在传统方法失效的多光源环境中仍具泛化能力。代码已开源。
原文摘要 · Abstract (English)
Shadow removal under diverse lighting conditions requires disentangling illumination from intrinsic reflectance, a challenge compounded when physical priors are not properly aligned. We propose PhaSR (Physically Aligned Shadow Removal), addressing this through dual-level prior alignment to enable robust performance from single-light shadows to multi-source ambient lighting. First, Physically Aligned Normalization (PAN) performs closed-form illumination correction via Gray-world normalization, log-domain Retinex decomposition, and dynamic range recombination, suppressing chromatic bias. Second, Geometric-Semantic Rectification Attention (GSRA) extends differential attention to cross-modal alignment, harmonizing depth-derived geometry with DINO-v2 semantic embeddings to resolve modal conflicts under varying illumination. Experiments show competitive performance in shadow removal with lower complexity and generalization to ambient lighting where traditional methods fail under multi-source illumination. Our source code is available at https://github.com/ming053l/PhaSR.
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。