Isometric multi-shape matching

Gao M, Laehner Z, Thunberg J, Cremers D, Bernard F (2021)

Publication Type: Conference contribution

Publication year: 2021

Journal

Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition IEEE Computer Society; 1999

Publisher: IEEE Computer Society

Pages Range: 14178-14188

Conference Proceedings Title: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

Event location: Virtual, Online, USA

ISBN: 9781665445092

DOI: 10.1109/CVPR46437.2021.01396

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-ofthe-art in isometric multi-shape matching.

Involved external institutions

Technische Universität München (TUM) DE Germany (DE) Halmstad University / Högskolan i Halmstad SE Sweden (SE)

How to cite

APA:

Gao, M., Laehner, Z., Thunberg, J., Cremers, D., & Bernard, F. (2021). Isometric multi-shape matching. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (pp. 14178-14188). Virtual, Online, USA: IEEE Computer Society.

MLA:

Gao, Maolin, et al. "Isometric multi-shape matching." Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2021, Virtual, Online, USA IEEE Computer Society, 2021. 14178-14188.

BibTeX: Download