通过光照与几何迭代推理，精准区分投射影与附着影。
Cast and Attached Shadow Detection via Iterative Light and Geometry Reasoning
- 构建光照与阴影检测的双向反馈机制，利用表面法向与光方向关系推断阴影
- 在1458张图像上实现附着影误报率降低至少33%，整体性能更优
- 适合需要精确阴影分析的场景理解、三维重建任务
阴影蕴含丰富的场景几何与光照信息，但现有方法或仅预测统一阴影掩码，或完全忽略附着阴影。本文提出一种联合检测投射影与附着影的框架，基于主导方向光假设下对光照方向与表面几何的显式物理建模。核心思路是：背向光源的表面易陷入阴影。我们利用阴影生成与光照估计之间的互逆关系，构建闭环反馈循环，采用双模块架构——阴影检测模块与光照估计模块相互迭代优化。每轮中，更新的光照估计结合表面法向生成部分附着阴影图以指导检测，而改进的阴影预测又反向提升光照估计精度。为支持训练与评估，我们引入一个包含1458张图像的数据集，标注来自三个现有基准的投射影与附着影掩码。实验表明，所提方法显著优于已有方法，附着影误报率（BER）至少降低33%，同时保持出色的全影与投射影检测性能。
原文摘要 · Abstract (English)
Shadows encode rich information about scene geometry and illumination, yet existing methods either predict a unified shadow mask or overlook attached shadows entirely. We address this gap by proposing a framework for jointly detecting cast and attached shadows through explicit physical modeling of light direction and surface geometry under a dominant directional-light setting. Our approach is grounded in a simple observation: surfaces facing away from the light source tend to fall into shadow. We exploit the reciprocal relationship between shadow formation and light estimation to construct a closed feedback loop, a dual-module architecture in which a shadow detection module and a light estimation module iteratively refine each other. At each pass, updated light estimates, together with surface normals, produce partial attached shadow maps that guide detection, while improved shadow predictions sharpen light estimation. To support training and evaluation, we introduce a dataset of 1,458 images with manually annotated cast and attached shadow masks sourced from three existing benchmarks. Experiments demonstrate that our proposed method outperforms prior methods, with at least a 33% reduction in attached-shadow BER, while maintaining strong full-shadow and cast-shadow performance.
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。