DWKS : A Local Descriptor of Deformations Between Meshes and Point Clouds
Robin Magnet, Maks Ovsjanikov
Abstract
We propose a novel pointwise descriptor, called DWKS, aimed at finding correspondences across two deformable shape collections. Unlike the majority of existing descriptors, rather than capturing local geometry, DWKS captures the deformation around a point within a collection in a multi-scale and informative manner. This, in turn, allows to compute inter-collection correspondences without using landmarks. To this end, we build upon the successful spectral WKS descriptors, but rather than using the Laplace-Beltrami operator, show that a similar construction can be performed on shape difference operators, that capture differences or distortion within a collection. By leveraging the collection information our descriptor facilitates difficult non-rigid shape matching tasks, even in the presence of strong partiality and significant deformations. We demonstrate the utility of our approach across a range of challenging matching problems on both meshes and point clouds.
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.
Builds on5
- Unsupervised Deep Learning for Structured Shape MatchingJean-Michel Roufosse, Abhishek Sharma, Maks OvsjanikovICCV 2019 · 160 citations
- Weakly Supervised Deep Functional Maps for Shape MatchingAbhishek Sharma, Maks OvsjanikovNeurIPS 2020 · 58 citations
- OperatorNet: Recovering 3D Shapes From Difference OperatorsRuqi Huang, Marie-Julie Rakotosaona, Panos Achlioptas, Leonidas J. Guibas et al.ICCV 2019 · 21 citations
- Deep Geometric Functional Maps: Robust Feature Learning for Shape CorrespondenceNicolas Donati, Abhishek Sharma, Maks OvsjanikovCVPR 2020
- Isometric Multi-Shape MatchingMaolin Gao, Zorah Lähner, Johan Thunberg, Daniel Cremers et al.CVPR 2021
Related papers
- Efficient and Robust Shape Correspondence via Sparsity-Enforced Quadratic AssignmentRui Xiang, Rongjie Lai, Hongkai ZhaoCVPR 2020
- Probabilistic Deformation Consistency for Unsupervised Shape MatchingYifan Xia, Tianwei Ye, Jun Huang, Xiaoguang Mei et al.AAAI 2026
- Non-Rigid Shape Registration via Deep Functional Maps PriorPuhua Jiang, Mingze Sun, Ruqi HuangNeurIPS 2023 · 23 citations
- Shape correspondence using anisotropic Chebyshev spectral CNNsQinsong Li, Shengjun Liu, Ling Hu, Xinru LiuCVPR 2020
- Unsupervised Learning of Robust Spectral Shape MatchingDongliang Cao, Paul Roetzer, Florian BernardSIGGRAPH 2023 · 45 citations
