无需光照校准，用神经网络从多视角图像重建三维形状与材质。
Neural Multi-View Self-Calibrated Photometric Stereo without Photometric Stereo Cues
- 用神经隐式场联合建模几何、材质和光照，直接从原始图像优化。
- 在形状和光照估计上优于现有方法，且能处理复杂材质和非对齐视角。
- 适合需要高精度三维重建的科研与工业应用，尤其无光照标定场景。
我们提出一种神经逆渲染方法，从不同方向光照下的多视角图像中联合重建几何、空间变化的反射特性以及光照条件。与以往需要光照校准或中间提示（如每视图法线图）的多视角光度立体方法不同，本方法在单阶段内仅从原始图像联合优化所有场景参数。我们使用神经隐式场表示几何与反射特性，并引入阴影感知体渲染。一个空间网络首先预测每个场景点的有符号距离和反射潜码；随后，反射网络根据潜码及编码后的表面法线、视角和光照方向估计反射值。所提方法在形状和光照估计精度上超越当前最先进的法线引导方法，可推广至视角不对齐的多光源图像，且能处理具有挑战性的几何与反射特性。
原文摘要 · Abstract (English)
We propose a neural inverse rendering approach that jointly reconstructs geometry, spatially varying reflectance, and lighting conditions from multi-view images captured under varying directional lighting. Unlike prior multi-view photometric stereo methods that require light calibration or intermediate cues such as per-view normal maps, our method jointly optimizes all scene parameters from raw images in a single stage. We represent both geometry and reflectance as neural implicit fields and apply shadow-aware volume rendering. A spatial network first predicts the signed distance and a reflectance latent code for each scene point. A reflectance network then estimates reflectance values conditioned on the latent code and angularly encoded surface normal, view, and light directions. The proposed method outperforms state-of-the-art normal-guided approaches in shape and lighting estimation accuracy, generalizes to view-unaligned multi-light images, and handles objects with challenging geometry and reflectance.
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。