PointTriNet: Learned Triangulation of 3D Point Sets (ECCV 2020) - CrossMinds.ai
PointTriNet: Learned Triangulation of 3D Point Sets (ECCV 2020)
Aug 18, 202011 views
by Nicholas Sharp and Maks Ovsjanikov
presented at ECCV 2020

webpage: http://nmwsharp.com/research/learned-triangulation
arxiv: http://arxiv.org/abs/2005.02138
code: http://github.com/nmwsharp/learned-triangulation
(including pretrained model)

Abstract: This work considers a new task in geometric deep learning: generating a triangulation among a set of points in 3D space. We present PointTriNet, a differentiable and scalable approach enabling point set triangulation as a layer in 3D learning pipelines. The method iteratively applies two neural networks: a classification network predicts whether a candidate triangle should appear in the triangulation, while a proposal network suggests additional candidates. Both networks are structured as PointNets over nearby points and triangles, using a novel triangle-relative input encoding. Since these learning problems operate on local geometric data, our method is efficient and scalable, and generalizes to unseen shape categories. Our networks are trained in an unsupervised manner from a collection of shapes represented as point clouds. We demonstrate the effectiveness of this approach for classical meshing tasks, robustness to outliers, and as a component in end-to-end learning systems.
ECCV 2020