VortSDF: 3D Modeling with Centroidal Voronoi Tesselation on Signed Distance Field
This work addresses the limitation of voxel-based methods in complex scenes for researchers and practitioners in 3D modeling and multi-view reconstruction, offering an incremental improvement.
The paper tackles the precision-complexity trade-off in volumetric shape representations for 3D reconstruction by using Centroidal Voronoi Tesselation (CVT) to discretize space more efficiently around surfaces, resulting in unprecedented reconstruction quality validated by Chamfer statistics on objects, open scenes, and humans.
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.