CVPR2021

MongeNet: Efficient Sampler for Geometric Deep Learning

Léo Lebrat, Rodrigo Santa Cruz, Clinton Fookes, Olivier Salvado

Abstract

equal contribution https://lebrat.github.io/MongeNet Figure 1: Discretization of a mesh by a point cloud. Left: MongeNet discretization. Right: Classical random uniform discretization. The resulting Voronoi Tessellations spawn on the triangles of the mesh are shown in red.