VisCo Grids: Surface Reconstruction with Viscosity and Coarea GridsDownload PDF

Published: 31 Oct 2022, Last Modified: 10 Jan 2023NeurIPS 2022 AcceptReaders: Everyone
Keywords: surface reconstruction, implicit neural representations, signed distance functions
Abstract: Surface reconstruction has been seeing a lot of progress lately by utilizing Implicit Neural Representations (INRs). Despite their success, INRs often introduce hard to control inductive bias (i.e., the solution surface can exhibit unexplainable behaviours), have costly inference, and are slow to train. The goal of this work is to show that replacing neural networks with simple grid functions, along with two novel geometric priors achieve comparable results to INRs, with instant inference, and improved training times. To that end we introduce VisCo Grids: a grid-based surface reconstruction method incorporating Viscosity and Coarea priors. Intuitively, the Viscosity prior replaces the smoothness inductive bias of INRs, while the Coarea favors a minimal area solution. Experimenting with VisCo Grids on a standard reconstruction baseline provided comparable results to the best performing INRs on this dataset.
TL;DR: We introduce VisCo, a grid-based surface reconstruction method incorporating viscosity and coarea priors.
Supplementary Material: zip
14 Replies

Loading