Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Isometric multi-shape matching

Gao, Maolin ; Lähner, Zorah ; Thunberg, Johan LU ; Cremers, Daniel and Bernard, Florian (2021) 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2021 p.14183-14193
Abstract
Finding correspondences between shapes is a fundamental problem in computer vision and graphics, which is relevant for many applications, including 3D reconstruction, object tracking, and style transfer. The vast majority of correspondence methods aim to find a solution between pairs of shapes, even if multiple instances of the same class are available. While isometries are often studied in shape correspondence problems, they have not been considered explicitly in the multi-matching setting. This paper closes this gap by proposing a novel optimisation formulation for isometric multi-shape matching. We present a suitable optimisation algorithm for solving our formulation and provide a convergence and complexity analysis. Our algorithm... (More)
Finding correspondences between shapes is a fundamental problem in computer vision and graphics, which is relevant for many applications, including 3D reconstruction, object tracking, and style transfer. The vast majority of correspondence methods aim to find a solution between pairs of shapes, even if multiple instances of the same class are available. While isometries are often studied in shape correspondence problems, they have not been considered explicitly in the multi-matching setting. This paper closes this gap by proposing a novel optimisation formulation for isometric multi-shape matching. We present a suitable optimisation algorithm for solving our formulation and provide a convergence and complexity analysis. Our algorithm obtains multi-matchings that are by construction provably cycle-consistent. We demonstrate the superior performance of our method on various datasets and set the new state-of-the-art in isometric multi-shape matching. (Less)
Please use this url to cite or link to this publication:
author
; ; ; and
publishing date
type
Chapter in Book/Report/Conference proceeding
publication status
published
subject
host publication
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition
pages
11 pages
publisher
IEEE - Institute of Electrical and Electronics Engineers Inc.
conference name
2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2021
conference location
Virtual, Online, United States
conference dates
2021-06-19 - 2021-06-25
external identifiers
  • scopus:85117637730
ISBN
978-1-6654-4509-2
DOI
10.1109/CVPR46437.2021.01396
language
English
LU publication?
no
id
2ab5d916-9552-42dd-860b-266f1463b1c5
date added to LUP
2024-09-05 14:03:02
date last changed
2025-04-04 14:38:56
@inproceedings{2ab5d916-9552-42dd-860b-266f1463b1c5,
  abstract     = {{Finding correspondences between shapes is a fundamental problem in computer vision and graphics, which is relevant for many applications, including 3D reconstruction, object tracking, and style transfer. The vast majority of correspondence methods aim to find a solution between pairs of shapes, even if multiple instances of the same class are available. While isometries are often studied in shape correspondence problems, they have not been considered explicitly in the multi-matching setting. This paper closes this gap by proposing a novel optimisation formulation for isometric multi-shape matching. We present a suitable optimisation algorithm for solving our formulation and provide a convergence and complexity analysis. Our algorithm obtains multi-matchings that are by construction provably cycle-consistent. We demonstrate the superior performance of our method on various datasets and set the new state-of-the-art in isometric multi-shape matching.}},
  author       = {{Gao, Maolin and Lähner, Zorah and Thunberg, Johan and Cremers, Daniel and Bernard, Florian}},
  booktitle    = {{Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition}},
  isbn         = {{978-1-6654-4509-2}},
  language     = {{eng}},
  pages        = {{14183--14193}},
  publisher    = {{IEEE - Institute of Electrical and Electronics Engineers Inc.}},
  title        = {{Isometric multi-shape matching}},
  url          = {{http://dx.doi.org/10.1109/CVPR46437.2021.01396}},
  doi          = {{10.1109/CVPR46437.2021.01396}},
  year         = {{2021}},
}