scene

shapes

image retrieval

view synthesis

surface reconstruction

rgb-d

lego

ind eng chem

point cloud_60597

expedition

welfare state

identity construction

reconstruction_39619

magnetic_116536

texture_61553

independent component analysis

rapid transit

boron-doped diamond

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).

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