English

CCuantuMM: Cycle-Consistent Quantum-Hybrid Matching of Multiple Shapes

Computer Vision and Pattern Recognition 2023-03-29 v1

Abstract

Jointly matching multiple, non-rigidly deformed 3D shapes is a challenging, NP\mathcal{NP}-hard problem. A perfect matching is necessarily cycle-consistent: Following the pairwise point correspondences along several shapes must end up at the starting vertex of the original shape. Unfortunately, existing quantum shape-matching methods do not support multiple shapes and even less cycle consistency. This paper addresses the open challenges and introduces the first quantum-hybrid approach for 3D shape multi-matching; in addition, it is also cycle-consistent. Its iterative formulation is admissible to modern adiabatic quantum hardware and scales linearly with the total number of input shapes. Both these characteristics are achieved by reducing the NN-shape case to a sequence of three-shape matchings, the derivation of which is our main technical contribution. Thanks to quantum annealing, high-quality solutions with low energy are retrieved for the intermediate NP\mathcal{NP}-hard objectives. On benchmark datasets, the proposed approach significantly outperforms extensions to multi-shape matching of a previous quantum-hybrid two-shape matching method and is on-par with classical multi-matching methods.

Keywords

Cite

@article{arxiv.2303.16202,
  title  = {CCuantuMM: Cycle-Consistent Quantum-Hybrid Matching of Multiple Shapes},
  author = {Harshil Bhatia and Edith Tretschk and Zorah Lähner and Marcel Seelbach Benkner and Michael Moeller and Christian Theobalt and Vladislav Golyanik},
  journal= {arXiv preprint arXiv:2303.16202},
  year   = {2023}
}

Comments

Computer Vision and Pattern Recognition (CVPR) 2023; 22 pages, 24 figures and 5 tables; Project page: https://4dqv.mpi-inf.mpg.de/CCuantuMM/

R2 v1 2026-06-28T09:38:32.920Z