发表机构
Jilin University; Guangdong Institute of Intelligence Science and Technology; Beijing Institute of Technology; The Hong Kong University of Science and Technology（吉林大学; 广东智能科学与技术研究院; 北京理工大学; 香港科技大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对事件相机光度立体视觉中事件稀疏且依赖未知阈值的问题，提出PIE-PS框架，通过物理辐照度事件特征和PIE-GNN图网络，利用可靠性分级注意力聚合，实现稠密法线重建，性能优于现有方法。
AI 中文摘要
事件相机以微秒级延迟和高动态范围记录异步的对数图像辐照度变化。这些特性在移动光照下的光度立体视觉中很有用，但原始事件是稀疏的，并且依赖于未知的对比度阈值。我们从事件触发模型出发，推导出相邻事件、光运动和表面法线之间的物理关系。这种关系给出了一个直接的纯物理求解器，但该求解器需要阈值、每个像素处有足够的事件，并且需要独立的逐像素优化。为了解决这些限制，我们引入了PIE-PS，一个基于学习的框架，用于从原始事件流和已知光照中重建稠密表面法线。我们通过将同一像素处的两个相邻事件与其对应的光方向配对来形成物理辐照度事件（PIE）。每个PIE提供一个物理辐照度事件特征（PIEF），定义为带符号的事件率。PIEF不需要未知的对比度阈值。为了在邻近的PIE之间共享空间和时间上下文，我们引入了PIE-GNN，它将每个PIE视为一个图节点，并用其光对几何进行编码。由于PIE观测的可靠性可能随局部外观、光照几何和传感器噪声而变化，可靠性分级注意力（RGA）预测可靠性权重，以降低不可靠PIE的权重。然后，像素聚合产生稠密法线。在合成和真实数据上的实验表明，PIE-PS优于先前基于事件的光度立体视觉方法和直接求解器基线。
英文摘要
Event cameras record asynchronous log-image-irradiance changes with microsecond latency and high dynamic range. These properties are useful for photometric stereo under moving illumination, but raw events are sparse and depend on an unknown contrast threshold. We start from the event trigger model and derive a physical relation between adjacent events, light motion, and surface normals. This relation gives a direct physics-only solver, but the solver needs the threshold, enough events at each pixel, and independent per-pixel optimization. To address these limits, we introduce PIE-PS, a learning-based framework for dense surface normal reconstruction from raw event streams and known lighting. We form Physical Irradiance Events (PIEs) by pairing two adjacent events at the same pixel with their corresponding light directions. Each PIE provides a Physical Irradiance Event Feature (PIEF), defined as the signed event rate. PIEF does not require the unknown contrast threshold. To share spatial and temporal context across nearby PIEs, we introduce PIE-GNN, which treats each PIE as a graph node and encodes it with its light-pair geometry. Since the reliability of PIE observations can vary with local appearance, illumination geometry, and sensor noise, Reliability-Grading Attention (RGA) predicts reliability weights to down-weight unreliable PIEs. Pixel aggregation then produces dense normals. Experiments on synthetic and real data show that PIE-PS outperforms prior event-based photometric stereo methods and the direct solver baseline.
Comments9 pages, 7 figures. Accepted to SIGGRAPH Asia 2026 Conference Papers
