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

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).

Automated summary

This paper presents an efficient method for jointly optimizing topology, materials and lighting from multi-view image observations. The proposed approach outputs triangle meshes with spatially-varying materials and environment lighting that can be used in any traditional graphics engine. By leveraging recent advancements in differentiable rendering and differentiable marching tetrahedrons, the authors enable gradient-based optimization directly on the surface mesh and efficiently recover all-frequency lighting.