We present a novel method to obtain high-quality 3D reconstructions from consumer RGB-D sensors. Our core idea is to simultaneously optimize for geometry encoded in a signed distance field, textures from automatically-selected keyframes, and their camera poses along with material and scene lighting. To this end, we propose a joint surface reconstruction approach that utilizes Shape-from-Shading techniques and spatially-varying spherical harmonics. We demonstrate that our method dramatically improves both reconstructed scene geometry and surface texture.

This presentation is part of Minisymposium “MS57 - Recent Trends in Photometric 3D-reconstruction (2 parts)”
organized by: Jean-Denis Durou (IRIT, Université de Toulouse) , Maurizio Falcone (Dipartimento di Matematica, Università di Roma "La Sapienza") .

Authors:

Robert Maier (TU Munich)

Keywords:

3d reconstruction, computer vision, rgb-d, shading-based refinement, shape-from-shading