No Cover Image

Conference Paper/Proceeding/Abstract 1113 views 153 downloads

Shape Correspondence with Isometric and Non-Isometric Deformations

R. M. Dyke, C Stride, Y.-K. Lai, P. L. Rosin, M. Aubry, A. Boyarski, A. M. Bronstein, M. M. Bronstein, D. Cremers, M. Fisher, T. Groueix, D. Guo, V. G. Kim, R. Kimmel, Z. Lähner, K. Li, O. Litany, T. Remez, E. Rodolà, B. C. Russell, Y. Sahillioglu, R. Slossberg, M. Vestner, Z. Wu, J. Yang, Gary Tam Orcid Logo

Eurographics Workshop on 3D Object Retrieval

Swansea University Author: Gary Tam Orcid Logo

Check full text

DOI (Published version): 10.2312/3dor.20191069

Abstract

The registration of surfaces with non-rigid deformation, especially non-isometric deformations, is a challenging problem. When applying such techniques to real scans, the problem is compounded by topological and geometric inconsistencies between shapes. In this paper, we capture a benchmark dataset...

Full description

Published in: Eurographics Workshop on 3D Object Retrieval
ISBN: 978-3-03868-077-2
ISSN: 1997-0471
Published: The Eurographics Association 2019
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa52380
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract: The registration of surfaces with non-rigid deformation, especially non-isometric deformations, is a challenging problem. When applying such techniques to real scans, the problem is compounded by topological and geometric inconsistencies between shapes. In this paper, we capture a benchmark dataset of scanned 3D shapes undergoing various controlled deformations (articulating, bending, stretching and topologically changing), along with ground truth correspondences. With the aid of thistiered benchmark of increasingly challenging real scans, we explore this problem and investigate how robust current stateof-the-art methods perform in different challenging registration andc orrespondence scenarios. We discover that changes in topology is a challenging problem for some methods and that machine learning-based approaches prove to be more capable of handling non-isometric deformations on shapes that are moderately similar to the training set.
College: Faculty of Science and Engineering
Funders: This work has been supported by the Cardiff University EPSRC Doctoral Training Partnership [grant ref. EP/N509449/1], and by the Scientific and Technological Research Council of Turkey (TÜB˙ITAK) [grant ref. EEEAG-115E471].