3D Reconstruction by Parameterized Surface Mapping
P.-A. Langlois, M. Fisher, O. Wang, V. Kim, A. Boulch, R. Marlet, B. Russell
Published in International Conference on Image Processing (ICIP), 2021
We introduce an approach for computing a 3D mesh from one or more views of an object by establishing dense correspondences between pixels in the views and 3D locations on a learnable parameterized surface. We propose a multi-view shape encoder that can be jointly trained with the AtlasNet surface parameterization. The shape is further refined using a novel geometric cycle-consistency loss between the learnable parameterized surface and input views. We demonstrate the efficacy of our approach on the ShapeNet-COCO dataset.