Spectral Meets Spatial: Harmonising 3D Shape Matching and Interpolation
Dongliang Cao, Marvin Eisenberger, Nafie El Amrani, Daniel Cremers, Florian Bernard
Abstract
NeuroMorph Ours Source Target pose-dominant shape-dominant 3D shape interpolation 3D shape matching Source URSSM Ours Target Figure 1. Top: 3D shape interpolation. Compared to the SOTA shape interpolation method NeuroMorph [29], our method obtains more reliable interpolation even under large non-isometry. Bottom left: 3D shape matching. The point-wise correspondences found by the SOTA shape matching method URSSM [13] contains local mismatches. In contrast, our method enables smooth shape matching. Bottom right: 3D shape matching and interpolation.
Our method is the first unsupervised method that obtains both accurate correspondences (shown as texture transfer) and realistic interpolation that capture both the pose-dominant and shape-dominant deformations.
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 a9a15cba-4f0f-4242-bbb9-e01c05a3c124Cited by top-tier papers17
- DiffuMatch: Category-Agnostic Spectral Diffusion Priors for Robust Non-Rigid Shape MatchingEmery Pierson, Lei Li, Angela Dai, Maks OvsjanikovICCV 2025 · 5 citations
- Teaching DINOv3 About Partial 3D Geometry: A Self-Supervised Geometry-Aware ApproachViktoria Ehm, Dongliang Cao, Riccardo Marin, Daniel Scholz et al.CVPR 2026 · 2 citations
- RINO: Rotation-Invariant Non-Rigid CorrespondencesMaolin Gao, Shao Jie Hu-Chen, Congyue Deng, Riccardo Marin et al.CVPR 2026 · 2 citations
- Volumetric Functional MapsFilippo Maggioli, Simone Melzi, Marco LivesuCVPR 2026 · 2 citations
- From Feature Learning to Spectral Basis Learning: A Unifying and Flexible Framework for Efficient and Robust Shape MatchingFeifan Luo, Hongyang ChenCVPR 2026 · 2 citations
Builds on18
- Unsupervised Deep Learning for Structured Shape MatchingJean-Michel Roufosse, Abhishek Sharma, Maks OvsjanikovICCV 2019 · 160 citations
- 4DComplete: Non-Rigid Motion Estimation Beyond the Observable SurfaceYang Li, Hikari Takehara, Takafumi Taketomi, Bo Zheng et al.ICCV 2021 · 160 citations
- Deep Shells: Unsupervised Shape Correspondence with Optimal TransportMarvin Eisenberger, Aysim Toker, Laura Leal-Taixé, Daniel CremersNeurIPS 2020 · 107 citations
- Shape Registration in the Time of TransformersGiovanni Trappolini, Luca Cosmo, Luca Moschella, Riccardo Marin et al.NeurIPS 2021 · 77 citations
- Learning Multi-resolution Functional Maps with Spectral Attention for Robust Shape MatchingLei Li, Nicolas Donati, Maks OvsjanikovNeurIPS 2022 · 57 citations
Related papers
- NeuroMorph: Unsupervised Shape Interpolation and Correspondence in One GoMarvin Eisenberger, David Novotný, Gael Kerchenbaum, Patrick Labatut et al.CVPR 2021
- Stable-SCore: A Stable Registration-based Framework for 3D Shape CorrespondenceHaolin Liu, Xiaohang Zhan, Zizheng Yan, Zhongjin Luo et al.CVPR 2025
- SGSoft: Learning Fused Semantic-Geometric Features for 3D Shape Correspondence via Template-Guided Soft SignalsSoyeon Yoon, Chang Wook Seo, Hyunjung ShimCVPR 2026 · 1 citation
- Probabilistic Deformation Consistency for Unsupervised Shape MatchingYifan Xia, Tianwei Ye, Jun Huang, Xiaoguang Mei et al.AAAI 2026
- DiffCorr: Conditional Diffusion Model with Reliable Pseudo-Label Guidance for Unsupervised Point Cloud Shape CorrespondenceJiacheng Deng, Jiahao Lu, Zhixin Cheng, Wenfei YangAAAI 2025 · 4 citations
