PointTriNet: Learned Triangulation of 3D Point Sets
This addresses a new task in geometric deep learning for researchers and practitioners in 3D computer vision and graphics, though it appears incremental as it builds on existing point cloud methods.
The paper tackles the problem of generating triangulations from 3D point sets by introducing PointTriNet, a differentiable and scalable method that uses neural networks to predict and propose triangles, enabling integration into 3D learning pipelines and demonstrating effectiveness in meshing tasks and robustness to outliers.
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.