-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Thomas_2025_WACV, author = {Thomas, Diego and Toussaint, Briac and Franco, Jean-Sebastien and Boyer, Edmond}, title = {VortSDF: 3D Modeling with Centroidal Voronoi Tesselation on Signed Distance Field}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {495-504} }
VortSDF: 3D Modeling with Centroidal Voronoi Tesselation on Signed Distance Field
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 Tessellation (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.
Related Material