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

Going Deeper with Point Networks

Le, E-T; Kokkinos, I; Mitra, NJ; (2020) Going Deeper with Point Networks. In: 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). (pp. pp. 9500-9509). IEEE Green open access

This is the latest version of this eprint.

[img]
Preview
Text
GoingDeeperwithLeanPointNetworks_PaperSupp (1).pdf - Accepted version

Download (11MB) | Preview

Abstract

In this work we introduce Lean Point Networks (LPNs) to train deeper and more accurate point processing networks by relying on three novel point processing blocks that improve memory consumption, inference time, and accuracy: a convolution-type block for point sets that blends neighborhood information in a memory-efficient manner; a crosslink block that efficiently shares information across low- and high-resolution processing branches; and a multi-resolution point cloud processing block for faster diffusion of information. By combining these blocks, we design wider and deeper point-based architectures. We report systematic accuracy and memory consumption improvements on multiple publicly available segmentation tasks by using our generic modules as drop-in replacements for the blocks of multiple architectures (PointNet++, DGCNN, SpiderNet, PointCNN).

Type: Proceedings paper
Title: Going Deeper with Point Networks
Event: 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 13-19 June 2020, Seattle, WA, USA
Open access status: An open access version is available from UCL Discovery
DOI: 10.1109/CVPR42600.2020.00952
Publisher version: https://doi.org/10.1109/CVPR42600.2020.00952
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: Three-dimensional displays, Convolution, Memory management, Computer vision, Training, Two dimensional displays
UCL classification: UCL
UCL > Provost and Vice Provost Offices
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
URI: https://discovery.ucl.ac.uk/id/eprint/10114750

Available Versions of this Item

Downloads since deposit
6Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item