Isometric Multi-Shape Matching
Maolin Gao, Zorah Lähner, Johan Thunberg, Daniel Cremers, Florian Bernard
Abstract
Figure 1 . Left: We present a novel approach for isometric multi-shape matching based on matching each shape to a (virtual) universe shape (shown semi-transparent). Our formulation represents point-to-point correspondences between shapes i and j as the composition of the shape-to-universe permutation matrix Pi and the universe-to-shape permutation matrix P T j . By doing so, the pairwise matchings Pij = PiP ⊤ j are by construction cycle-consistent. Middle: Our formulation successfully solves isometric multi-matching of partial shapes. Right: Due to the cycle-consistency we can use our correspondences to faithfully transfer textures across a shape collection.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Your agent calls
Luneget_paper_fulltext
Free to start. No credit card required.
Terminal
Install the CLIlune papers fulltext bb681042-3c13-4a88-b53e-d2841b3af7a4Cited by top-tier papers21
- Unsupervised Learning of Robust Spectral Shape MatchingDongliang Cao, Paul Roetzer, Florian BernardSIGGRAPH 2023 · 45 citations
- Spatially and Spectrally Consistent Deep Functional MapsMingze Sun, Shiwei Mao, Puhua Jiang, Maks Ovsjanikov et al.ICCV 2023 · 37 citations
- A Scalable Combinatorial Solver for Elastic Geometrically Consistent 3D Shape MatchingPaul Roetzer, Paul Swoboda, Daniel Cremers, Florian BernardCVPR 2022 · 22 citations
- Sparse Quadratic Optimisation over the Stiefel Manifold with Application to Permutation SynchronisationFlorian Bernard, Daniel Cremers, Johan ThunbergNeurIPS 2021 · 16 citations
- GenCorres: Consistent Shape Matching via Coupled Implicit-Explicit Shape Generative ModelsHaitao Yang, Xiangru Huang, Bo Sun, Chandrajit L. Bajaj et al.ICLR 2024 · 12 citations
Builds on4
- Unsupervised Deep Learning for Structured Shape MatchingJean-Michel Roufosse, Abhishek Sharma, Maks OvsjanikovICCV 2019 · 160 citations
- Correspondence learning via linearly-invariant embeddingRiccardo Marin, Marie-Julie Rakotosaona, Simone Melzi, Maks OvsjanikovNeurIPS 2020 · 82 citations
- Graduated Assignment for Joint Multi-Graph Matching and Clustering with Application to Unsupervised Graph Matching Network LearningRunzhong Wang, Junchi Yan, Xiaokang YangNeurIPS 2020 · 39 citations
- Smooth Shells: Multi-Scale Shape Registration With Functional MapsMarvin Eisenberger, Zorah Lähner, Daniel CremersCVPR 2020
Related papers
- Fast Globally Optimal and Geometrically Consistent 3D Shape MatchingPaul Roetzer, Florian BernardICCV 2025 · 2 citations
- Multi-Shape Matching with Cycle Consistency Basis via Functional MapsYifan Xia, Tianwei Ye, Huabing Zhou, Zhongyuan Wang et al.AAAI 2025 · 3 citations
- DcMatch: Unsupervised Multi-Shape Matching with Dual-Level ConsistencyTianwei Ye, Yong Ma, Xiaoguang MeiAAAI 2026 · 1 citation
- EchoMatch: Partial-to-Partial Shape Matching via Correspondence ReflectionYizheng Xie, Viktoria Ehm, Paul Roetzer, Nafie El Amrani et al.CVPR 2025
- Partial-to-Partial Shape Matching with Geometric ConsistencyViktoria Ehm, Maolin Gao, Paul Roetzer, Marvin Eisenberger et al.CVPR 2024
