TY - JOUR TI - Differentiable Surface Triangulation UR - https://doi.org/10.1145/3478513.3480554 PB - ASSOC COMPUTING MACHINERY A1 - Rakotosaona, Marie-Julie A1 - Aigerman, Noam A1 - Mitra, Niloy J A1 - Ovsjanikov, Maks A1 - Guerrero, Paul IS - 6 KW - Science & Technology KW - Technology KW - Computer Science KW - Software Engineering KW - Computer Science KW - meshing KW - geometry processing KW - surface representation KW - neural networks KW - VORONOI KW - COMPUTATION KW - MESHES SN - 0730-0301 EP - 13 AV - public N1 - This version is the author accepted manuscript. For information on re-use, please refer to the publisher?s terms and conditions. JF - ACM Transactions on Graphics Y1 - 2021/12/01/ N2 - Triangle meshes remain the most popular data representation for surface geometry. This ubiquitous representation is essentially a hybrid one that decouples continuous vertex locations from the discrete topological triangulation. Unfortunately, the combinatorial nature of the triangulation prevents taking derivatives over the space of possible meshings of any given surface. As a result, to date, mesh processing and optimization techniques have been unable to truly take advantage of modular gradient descent components of modern optimization frameworks. In this work, we present a differentiable surface triangulation that enables optimization for any per-vertex or per-face differentiable objective function over the space of underlying surface triangulations. Our method builds on the result that any 2D triangulation can be achieved by a suitably perturbed weighted Delaunay triangulation. We translate this result into a computational algorithm by proposing a soft relaxation of the classical weighted Delaunay triangulation and optimizing over vertex weights and vertex locations. We extend the algorithm to 3D by decomposing shapes into developable sets and differentiably meshing each set with suitable boundary constraints. We demonstrate the efficacy of our method on various planar and surface meshes on a range of difficult-to-optimize objective functions. Our code can be found online: https://github.com/mrakotosaon/diff-surface-triangulation. VL - 40 ID - discovery10159072 ER -