Non-Rigid Shape Correspondence

Follow this topic Ask about this topic

Non-rigid shape correspondence finds which points or regions on different 3D shapes represent the same location despite changes in pose, deformation, or partial visibility. Methods include spectral and functional maps built from surface geometry, learned descriptors with contrastive or coarse-to-fine matching, and deformation or transport-based registration; newer approaches also use semantic cues from vision and language models. These methods are evaluated on human and animal meshes, scans, and deforming sequences, including settings represented by benchmarks such as SMAL, TOPKIDS, and 4DMatch. A central challenge is that geometric methods can struggle with strong non-isometric changes, missing regions, and topology differences, while semantic guidance can help but may not transfer reliably across categories.

Latest papers

37 papers3 papers in the last four weeks, down 25% on the four weeks before. 0.0% of all new papers.

Unsupervised Contrastive Learning for Efficient and Robust Spectral Shape Matching
Mar 19, 2026Feifan Luo, Hongyang ChenFunctional Maps Non-Rigid Shape Correspondence
College of Computer Science and Technology, Zhejiang University, Hangzhou 310027, China · Research Center for Data Hub and Security, Zhejiang Lab, Hangzhou 311121, China
Feed-forward Gaussian Registration for Head Avatar Creation and Editing
Mar 16, 2026Malte Prinzler, Paulo Gotardo, Siyu Tang +13D Avatar Generation Multi-View 3D Reconstruction
ETH Zürich · Google
SGMatch: Semantic-Guided Non-Rigid Shape Matching with Flow Regularization
Mar 13, 2026Tianwei Ye, Xiaoguang Mei, Yifan Xia +3Functional Maps Geometric Representation Learning
Wuhan University, Wuhan 430072, China
GLASS: Graph and Vision-Language Assisted Semantic Shape Correspondence
Mar 8, 2026Qinfeng Xiao, Guofeng Mei, Qilong Liu +53D Shape Matching Semantic Correspondence
Hong Kong Polytechnic University, HK SAR · Fondazione Bruno Kessler, Italy · Laboratory for Artificial Intelligence in Design, HK SAR +1
Universal 3D Shape Matching via Coarse-to-Fine Language Guidance
Feb 22, 2026Qinfeng Xiao, Guofeng Mei, Bo Yang +33D Shape Matching Semantic Correspondence
Hong Kong Polytechnic University, HK SAR · Fondazione Bruno Kessler, Italy · University of Technology Sydney, Australia
FUSE: A Flow-based Mapping Between Shapes
Nov 17, 2025Lorenzo Olearo, Giulio Viganò, Daniele Baieri +2Flow Matching Non-Rigid Shape Correspondence
University of Milano-Bicocca, Milan, Italy · University of Bonn, Bonn, Germany · Lamarr Institute, Germany +1
Human Pose-Constrained UV Map Estimation
Jan 15, 2025Matej Suchanek, Miroslav Purkrabek, Jiri MatasNon-Rigid Shape Correspondence
Visual Recognition Group Department of Cybernetics Faculty of Electrical Engineering Czech Technical University in Prague

Mar 19, 2026J/K move · Enter open · S save

Unsupervised Contrastive Learning for Efficient and Robust Spectral Shape Matching

Feifan Luo, Hongyang Chen

College of Computer Science and Technology, Zhejiang University, Hangzhou 310027, China · Research Center for Data Hub and Security, Zhejiang Lab, Hangzhou 311121, China

Functional Maps Non-Rigid Shape Correspondence Contrastive Learning

Open paper AskPDF arXiv

Estimating correspondences between pairs of non-rigid deformable 3D shapes remains a significant challenge in computer vision and graphics. While deep functional map methods have become the go-to solution for addressing this problem, they primarily focus on optimizing pointwise and functional maps either individually or jointly, rather than directly enhancing feature representations in the embedding space, which often results in inadequate feature quality and suboptimal matching performance. Furthermore, these approaches heavily rely on traditional functional map techniques, such as time-consuming functional map solvers, which incur substantial computational costs. In this work, we introduce, for the first time, a novel unsupervised contrastive learning-based approach for efficient and robust 3D shape matching. We begin by presenting an unsupervised contrastive learning framework that promotes feature learning by maximizing consistency within positive similarity pairs and minimizing it within negative similarity pairs, thereby improving both the consistency and discriminability of the learned features.We then design a significantly simplified functional map learning architecture that eliminates the need for computationally expensive functional map solvers and multiple auxiliary functional map losses, greatly enhancing computational efficiency. By integrating these two components into a unified two-branch pipeline, our method achieves state-of-the-art performance in both accuracy and efficiency. Extensive experiments demonstrate that our approach is not only computationally efficient but also outperforms current state-of-the-art methods across various challenging benchmarks, including near-isometric, non-isometric, and topologically inconsistent scenarios, even surpassing supervised techniques.