PointTriNet: Learned Triangulation of 3D Point Sets

Nicholas Sharp, Maks Ovsjanikov

Research output: Chapter in Book/Report/Conference proceedingConference contribution

21 Scopus citations

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.
Original languageEnglish (US)
Title of host publicationComputer Vision – ECCV 2020
PublisherSpringer International Publishing
Pages762-778
Number of pages17
ISBN (Print)9783030585914
DOIs
StatePublished - Nov 3 2020
Externally publishedYes

Fingerprint

Dive into the research topics of 'PointTriNet: Learned Triangulation of 3D Point Sets'. Together they form a unique fingerprint.

Cite this