PointTriNet: Learned Triangulation of 3D Point Sets
Authors:
Preprint
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.Keywords
All Related Versions
This publication has 17 references indexed in Scilit:
- Learning Shape Templates With Structured Implicit Functions2019
- Mesh R-CNN2019
- A Survey of Surface Reconstruction from Point CloudsComputer Graphics Forum, 2016
- A survey of the marching cubes algorithmComputers & Graphics, 2006
- Provably good sampling and meshing of surfacesGraphical Models, 2005
- The power crust, unions of balls, and the medial axis transformComputational Geometry, 2001
- Surface Reconstruction by Voronoi FilteringDiscrete & Computational Geometry, 1999
- The ball-pivoting algorithm for surface reconstructionIEEE Transactions on Visualization and Computer Graphics, 1999
- Regularised marching tetrahedra: improved iso-surface extractionComputers & Graphics, 1999
- On triangulating three-dimensional polygonsComputational Geometry, 1998