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

E3Sym: Leveraging E(3) invariance for unsupervised 3D planar reflective symmetry detection

Li, Ren-Wu, Zhang, Ling-Xiao, Li, Chunpeng, Lai, Yukun ORCID: https://orcid.org/0000-0002-2094-5680 and Gao, Lin 2023. E3Sym: Leveraging E(3) invariance for unsupervised 3D planar reflective symmetry detection. Presented at: International Conference on Computer Vision (ICCV), Paris, France, 2-6 October 2023. Proceedings of IEEE/CVF International Conference on Computer Vision. IEEE, pp. 14497-14507. 10.1109/ICCV51070.2023.01337

[thumbnail of E3Sym_ICCV2023.pdf]
Preview
PDF - Accepted Post-Print Version
Download (7MB) | Preview

Abstract

Detecting symmetrical properties is a fundamental task in 3D shape analysis. In the case of a 3D model with planar symmetries, each point has a corresponding mirror point w.r.t. a symmetry plane, and the correspondences remain invariant under any arbitrary Euclidean transformation. Our proposed method, E3Sym, aims to detect planar reflective symmetry in an unsupervised and end-to-end manner by leveraging E(3) invariance. E3Sym establishes robust point correspondences through the use of E(3) invariant features extracted from a lightweight neural network, from which the dense symmetry prediction is produced. We also introduce a novel and efficient clustering algorithm to aggregate the dense prediction and produce a detected symmetry set, allowing for the detection of an arbitrary number of planar symmetries while ensuring the method remains differentiable for end-to-end training. Our method also possesses the ability to infer reasonable planar symmetries from incomplete shapes, which remains challenging for existing methods. Extensive experiments demonstrate that E3Sym is both effective and robust, outperforming state-of-the-art methods.

Item Type: Conference or Workshop Item (Paper)
Date Type: Publication
Status: Published
Schools: Computer Science & Informatics
Publisher: IEEE
ISBN: 9798350307191
ISSN: 1550-5499
Date of First Compliant Deposit: 25 September 2023
Date of Acceptance: 14 July 2023
Last Modified: 21 Feb 2024 15:27
URI: https://orca.cardiff.ac.uk/id/eprint/162703

Actions (repository staff only)

Edit Item Edit Item

Downloads

Downloads per month over past year

View more statistics