Cardiff University | Prifysgol Caerdydd ORCA
Online Research @ Cardiff 
WelshClear Cookie - decide language by browser settings

PRS-Net: planar reflective symmetry detection net for 3D models

Gao, Lin, Zhang, Ling-Xiao, Meng, Hsien-Yu, Ren, Yi-Hui, Lai, Yukun ORCID: https://orcid.org/0000-0002-2094-5680 and Kobbelt, Leif 2021. PRS-Net: planar reflective symmetry detection net for 3D models. IEEE Transactions on Visualization and Computer Graphics 27 (6) , pp. 3007-3018. 10.1109/TVCG.2020.3003823

[thumbnail of PRS-Net-TVCG.pdf]
Preview
PDF - Accepted Post-Print Version
Download (44MB) | Preview

Abstract

In geometry processing, symmetry is a universal type of high-level structural information of 3D models and benefits many geometry processing tasks including shape segmentation, alignment, matching, and completion. Thus it is an important problem to analyze various symmetry forms of 3D shapes. Planar reflective symmetry is the most fundamental one. Traditional methods based on spatial sampling can be time-consuming and may not be able to identify all the symmetry planes. In this paper, we present a novel learning framework to automatically discover global planar reflective symmetry of a 3D shape. Our framework trains an unsupervised 3D convolutional neural network to extract global model features and then outputs possible global symmetry parameters, where input shapes are represented using voxels. We introduce a dedicated symmetry distance loss along with a regularization loss to avoid generating duplicated symmetry planes. Our network can also identify generalized cylinders by predicting their rotation axes. We further provide a method to remove invalid and duplicated planes and axes. We demonstrate that our method is able to produce reliable and accurate results. Our neural network based method is hundreds of times faster than the state-of-the-art methods, which are based on sampling. Our method is also robust even with noisy or incomplete input surfaces.

Item Type: Article
Date Type: Publication
Status: Published
Schools: Computer Science & Informatics
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
ISSN: 1077-2626
Funders: Royal Society
Date of First Compliant Deposit: 16 June 2020
Date of Acceptance: 2 June 2020
Last Modified: 08 Nov 2023 02:06
URI: https://orca.cardiff.ac.uk/id/eprint/132544

Citation Data

Cited 12 times in Scopus. View in Scopus. Powered By Scopus® Data

Actions (repository staff only)

Edit Item Edit Item

Downloads

Downloads per month over past year

View more statistics