VortSDF: 3D Modeling with Centroidal Voronoi Tesselation on Signed Distance Field

TL;DR

This paper introduces VortSDF, a novel 3D modeling approach using Centroidal Voronoi Tesselation on Signed Distance Fields, improving shape reconstruction accuracy over traditional voxel-based methods.

Contribution

It proposes a new discretization strategy with CVT for better shape surface focus and integrates it into a volumetric optimization framework combining SDF and color networks.

Findings

Unprecedented reconstruction quality demonstrated.

Effective handling of objects, open scenes, and human models.

Validated with Chamfer statistics.

Abstract

Volumetric shape representations have become ubiquitous in multi-view reconstruction tasks. They often build on regular voxel grids as discrete representations of 3D shape functions, such as SDF or radiance fields, either as the full shape model or as sampled instantiations of continuous representations, as with neural networks. Despite their proven efficiency, voxel representations come with the precision versus complexity trade-off. This inherent limitation can significantly impact performance when moving away from simple and uncluttered scenes. In this paper we investigate an alternative discretization strategy with the Centroidal Voronoi Tesselation (CVT). CVTs allow to better partition the observation space with respect to shape occupancy and to focus the discretization around shape surfaces. To leverage this discretization strategy for multi-view reconstruction, we introduce a volumetric optimization framework that combines explicit SDF fields with a shallow color network, in order to estimate 3D shape properties over tetrahedral grids. Experimental results with Chamfer statistics validate this approach with unprecedented reconstruction quality on various scenarios such as objects, open scenes or human.