VisCo Grids: Surface Reconstruction with Viscosity and Coarea Grids
This addresses the problem of slow training and costly inference in surface reconstruction for computer vision and graphics applications, though it appears incremental as it builds on existing grid-based approaches.
The paper tackles surface reconstruction by replacing neural networks with simple grid functions and two geometric priors (Viscosity and Coarea), achieving comparable results to state-of-the-art Implicit Neural Representations while enabling instant inference and improved training times.
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.