Extracting Triangular 3D Models, Materials, and Lighting From Images

作者：Jacob Munkberg, J. Hasselgren, Tianchang Shen, Jun Gao, Wenzheng Chen, Alex Evans, T. Müller, S. Fidler · 发表于：Computer Vision and Pattern Recognition · 年份：2021 · DOI：10.1109/CVPR52688.2022.00810 · 被引用次数：517 · 研究领域：Computer Science

We present an efficient method for joint optimization of topology, materials and lighting from multi-view image observations. Unlike recent multi-view reconstruction approaches, which typically produce entangled 3D representations encoded in neural networks, we output triangle meshes with spatially-varying materials and environment lighting that can be deployed in any traditional graphics engine unmodified. We leverage recent work in differentiable rendering, coordinate-based networks to compactly represent volumetric texturing, alongside differentiable marching tetrahedrons to enable gradient-based optimization directly on the surface mesh. Finally, we introduce a differentiable formulation of the split sum approximation of environment lighting to efficiently recover all-frequency lighting. Experiments show our extracted models used in advanced scene editing, material decomposition, and high quality view interpolation, all running at interactive rates in triangle-based renderers (rasterizers and path tracers).