UCL Discovery
UCL home » Library Services » Electronic resources » UCL Discovery

PCPNet Learning Local Shape Properties from Raw Point Clouds

Guerrero, P; Kleiman, Y; Ovsjanikov, M; Mitra, NJ; (2018) PCPNet Learning Local Shape Properties from Raw Point Clouds. Computer Graphics Forum , 37 (2) pp. 75-85. 10.1111/cgf.13343. Green open access

[thumbnail of Guerrero_PCPNET Learning Local Shape Properties from Raw Point Clouds_AAM.pdf]
Preview
Text
Guerrero_PCPNET Learning Local Shape Properties from Raw Point Clouds_AAM.pdf - Accepted version

Download (5MB) | Preview

Abstract

In this paper, we propose PCPNET, a deep‐learning based approach for estimating local 3D shape properties in point clouds. In contrast to the majority of prior techniques that concentrate on global or mid‐level attributes, e.g., for shape classification or semantic labeling, we suggest a patch‐based learning method, in which a series of local patches at multiple scales around each point is encoded in a structured manner. Our approach is especially well‐adapted for estimating local shape properties such as normals (both unoriented and oriented) and curvature from raw point clouds in the presence of strong noise and multi‐scale features. Our main contributions include both a novel multi‐scale variant of the recently proposed PointNet architecture with emphasis on local shape information, and a series of novel applications in which we demonstrate how learning from training data arising from well‐structured triangle meshes, and applying the trained model to noisy point clouds can produce superior results compared to specialized state‐of‐the‐art techniques. Finally, we demonstrate the utility of our approach in the context of shape reconstruction, by showing how it can be used to extract normal orientation information from point clouds.

Type: Article
Title: PCPNet Learning Local Shape Properties from Raw Point Clouds
Open access status: An open access version is available from UCL Discovery
DOI: 10.1111/cgf.13343
Publisher version: https://doi.org/10.1111/cgf.13343
Language: English
Additional information: This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions.
Keywords: Computing methodologies, Point-based models, Shape analysis, Computer systems organization, Neural networks
UCL classification: UCL
UCL > Provost and Vice Provost Offices > UCL BEAMS
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of the Built Environment
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of the Built Environment > Bartlett School Env, Energy and Resources
URI: https://discovery.ucl.ac.uk/id/eprint/10056723
Downloads since deposit
58Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item