Shape From Tracing: Towards Reconstructing 3D Object Geometry and SVBRDF Material from Images via Differentiable Path Tracing
This work addresses the challenge of reconstructing 3D object geometry and SVBRDF material from images for computer graphics and vision researchers, offering a path towards higher quality reconstructions despite computational costs.
This paper explores the use of differentiable path tracing to reconstruct fine geometric and material detail from low-resolution input views, achieving high-quality reconstructions in a few hours. The method successfully disentangles shading, shadow, and global illumination effects from material properties.
Reconstructing object geometry and material from multiple views typically requires optimization. Differentiable path tracing is an appealing framework as it can reproduce complex appearance effects. However, it is difficult to use due to high computational cost. In this paper, we explore how to use differentiable ray tracing to refine an initial coarse mesh and per-mesh-facet material representation. In simulation, we find that it is possible to reconstruct fine geometric and material detail from low resolution input views, allowing high-quality reconstructions in a few hours despite the expense of path tracing. The reconstructions successfully disambiguate shading, shadow, and global illumination effects such as diffuse interreflection from material properties. We demonstrate the impact of different geometry initializations, including space carving, multi-view stereo, and 3D neural networks. Finally, with input captured using smartphone video and a consumer 360? camera for lighting estimation, we also show how to refine initial reconstructions of real-world objects in unconstrained environments.