Non-Rigid Shape Correspondence

Ask about this topic

Overview

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

CardsList

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

  1. Dense4D: Pixel-Level 4D Human Correspondence

    Oct 15, 2026Rıza Alp Güler3D Point TrackingNon-Rigid Shape Correspondence

    Department of Computing, Imperial College London

  2. Context without Commitment: Robust Dense Correspondence under Non-Rigid Deformation

    Sep 29, 2026Yuzhen He, Sara HomscheidPoint Cloud LearningNon-Rigid Shape Correspondence

    Mannheim Institute for Intelligent Systems in Medicine (MIISM) Medical Faculty Mannheim, Heidelberg University, Mannheim, Germany

  3. NHO: A Neural Hamiltonian Operator for Anchor-based Region Localization and Dense Correspondence

    Sep 29, 2026Jing Li, Yawei Luo, Xiangze Meng +3Non-Rigid Shape CorrespondenceNeural Operators

    Jilin University · Zhejiang University · North China University of Technology

  4. Levy-Driven Correspondence Estimation for Registration

    Sep 26, 2026Qianliang Wu, Jiaqi Yang, Wankou Yang +4Non-Rigid Shape CorrespondencePoint Cloud Registration

    Nantong University · Northwestern Polytechnical University · Southeast University +2

  5. Revisiting Avatar-As-Image: High-Fidelity Registration is All You Need

    Sep 10, 2026Margaret Kostyrko, Yuxuan Xue, Garvita Tiwari +1Non-Rigid Shape Correspondence3D Human Reconstruction

    University of Tübingen · Tübingen AI Center · Max Planck Institute for Informatics

  6. BridgeMatch: Conditional Transport Bridges in Matching Matrix Space for 3D Deformable Registration

    Sep 10, 2026Qianliang Wu, Haobo Jiang, Guangwei Gao +5Conditional Flow MatchingNon-Rigid Shape Correspondence

    Nantong University · Nanyang Technological University · Nanjing University of Science and Technology +2

  7. TokenMatch: 3D Mesh Correspondence Transformer with Curvature-Guided Tokenisation

    Sep 3, 2026Adeela Islam, Zorah Lähner, Vittorio Murino +13D ViTsNon-Rigid Shape Correspondence

    1Italian Institute of Technology · University of Genoa · 6Max Planck Institute for Informatics, SIC +4

  8. TRACE: Artifact-Robust Statistical Shape Modeling from Imperfect Surface Scans - A Case Study in Craniosynostosis 3D Photography

    Aug 22, 2026Sanjay Bhandari, Nawazish Khan, Alzbeta Novotna +7Statistical Shape ModelingDeformable Shape Reconstruction

    Scientific Computing and Imaging Institute, University of Utah, SLC, UT, USA · Kahlert School of Computing, University of Utah, Salt Lake City, UT, USA · Division of Pediatric Plastic Surgery, UPMC Children’s Hospital of Pittsburgh, PA, USA

  9. Coupled Optimal Transport with Landmark Constraints

    Aug 20, 2026Xiang Gu, Jian Sun, Zongben XuOptimal TransportNon-Rigid Shape Correspondence

    School of Mathematics and Statistics, Xi’an Jiaotong University, China

  10. Structure-aware Riemannian Growth Fields for 4D Plant Modeling

    Aug 13, 2026Meng-Yu Jennifer Kuo, Ryo KawaharaPlant Phenotyping4D Reconstruction

    Nara Women’s University, Japan · Kyoto University, Japan

  11. SCALP: Semi-Supervised Statistical Shape Modeling from Imperfect 3D Photogrammetry via Landmark-Anchored Spectral Warp

    Jul 31, 2026Nawazish Khan, Sanjay Bhandari, Sarang Joshi +8Point Cloud LearningStatistical Shape Modeling

    Scientific Computing and Imaging Institute, University of Utah, Salt Lake City, UT 84112, USA · Kahlert School of Computing, University of Utah, Salt Lake City, UT 84112, USA · Department of Biomedical Engineering, University of Utah, Salt Lake City, UT 84112, USA +1

  12. Landmark shape spaces with induced metrics

    Jul 30, 2026Sarang Joshi, Peter W. Michor, Stefan SommerNon-Rigid Shape CorrespondenceRiemannian Geometry

  13. MDND: Unsupervised Learning Guided by Non-Differentiable Refinement for Shape Correspondence

    Jul 17, 2026Qinsong Li, Jing Meng, Haibo Wang +1Functional MapsNon-Rigid Shape Correspondence

    Big Data Institute, Central South University, Changsha, Hunan 410083, China · School of Mathematics and Statistics, Central South University, Changsha, Hunan 410083, China

  14. Emergent Region-Level Facial Correspondence in Frozen Vision Foundation Models

    Jul 15, 2026Izaldein Al-Zyoud, Abdulmotaleb El SaddikSemantic CorrespondenceVision Foundation Models

    MCRLab, School of Electrical Engineering and Computer Science University of Ottawa, Ottawa, ON, Canada

  15. TreeSRNF: Square-Root Normal Fields for Generative Modelling of the Geometric and Structural Variability in Tree-like 3D Objects

    Jul 15, 2026Tahmina Khanam, Hamid Laga, Mohammed Bennamoun +4Statistical Shape ModelingNon-Rigid Shape Correspondence

    Murdoch University, WA, Australia. · University of Western Australia, WA, Australia. · Johns Hopkins University, USA.

  16. RealSkin: Spatio-Spectral Partial Neural Adjoint Maps for Image-to-3D Attribute Transfer

    Jul 14, 2026Jing Li, Yawei Luo, Xiangze Meng +3Functional MapsNon-Rigid Shape Correspondence

    Jilin University, China · Zhejiang University, China · North China University of Technology, China

  17. RegHead: Non-Humanoid Head Blendshapes via Feed-Forward Registration

    Jul 13, 2026Jiahao Luo, Hao Zhang, Jianqi Chen +93D Avatar GenerationNon-Rigid Shape Correspondence

    1UCSC · 2UIUC · 3KAUST +1

  18. Hyper-Network Neural Functional Maps for Unsupervised Robust 3D Shape Matching

    Jun 29, 2026Dongliang Cao, Florian BernardFunctional MapsNon-Rigid Shape Correspondence

    University of Bonn, Germany

  19. Articulating then Matching: Zero-Shot Shape Matching for Uncurated Data

    Jun 28, 2026Qilong Liu, Qinfeng Xiao, Chenyuan Yi +2Non-Rigid Shape Correspondence3D Shape Matching

    Hong Kong Polytechnic University, HK SAR · Artificial Intelligence in Design, HK SAR

  20. Coarse-to-Fine: A Hybrid Self-Supervised Method for Non-rigid 3D Shape Matching

    Jun 25, 2026Feifan Luo, Ting Li, Zhao Li +1Self-Supervised LearningFunctional Maps

    Zhejiang University, China · Zhejiang Lab, China · Wenzhou University of Technology, China

  21. MeshLoom: Feed-Forward Non-Rigid Registration of Mesh Sequences

    Jun 15, 2026Jianqi Chen, Jiraphon Yenphraphai, Xiangjun Tang +4Non-Rigid Shape Correspondence3D Mesh Deformation

    KAUST, Saudi Arabia · Snap Inc., United States of America · Purdue University, United States of America

  22. SEMAGIC: Learning Semantically Consistent Deformable 3D Representations from In-the-Wild Images

    May 27, 2026Sky Cen, Wufei Ma, Guofeng Zhang +2Deformable Shape ReconstructionNon-Rigid Shape Correspondence

    Johns Hopkins University · CISPA Helmholtz Center for Information Security

  23. SGSoft: Learning Fused Semantic-Geometric Features for 3D Shape Correspondence via Template-Guided Soft Signals

    May 18, 2026Soyeon Yoon, Chang Wook Seo, Hyunjung ShimGeometric Representation LearningNon-Rigid Shape Correspondence

    1KAIST AI · 2Anigma Technologies

  24. Min Generalized Sliced Gromov Wasserstein: A Scalable Path to Gromov Wasserstein

    May 13, 2026Ashkan Shahbazi, Xinran Liu, Ping He +1Non-Rigid Shape CorrespondenceOptimal Transport

    Department of Computer Science, College of Connected Computing, Vanderbilt University · Department of Electrical and Computer Engineering, Vanderbilt University

  25. Registration-Free Learnable Multi-View Capture of Faces in Dense Semantic Correspondence

    May 2, 2026Panagiotis P. Filntisis, George Retsinas, Radek Daněček +3Test-Time Optimization3D Reconstruction

    Institute of Robotics, Athena Research Center, 15125 Maroussi, Greece · HERON – Hellenic Robotics Center of Excellence, Athens, Greece · School of ECE, NTUA, Greece +3

  26. Face Anything: 4D Face Reconstruction from Any Image Sequence

    Apr 21, 2026Umut Kocasari, Simon Giebenhain, Richard Shaw +14D ReconstructionDeformable Shape Reconstruction

    Technical University of Munich, Germany · Huawei Noah’s Ark Lab, London, UK

  27. DeepShapeMatchingKit: Accelerated Functional Map Solver and Shape Matching Pipelines Revisited

    Apr 11, 2026Yizheng Xie, Lennart Bastian, Congyue Deng +3Functional MapsNon-Rigid Shape Correspondence

    Technical University of Munich · Simon Fraser University · Munich Center for Machine Learning +3

  28. Non-Rigid 3D Shape Correspondences: From Foundations to Open Challenges and Opportunities

    Apr 1, 2026Aleksei Zhuravlev, Lennart Bastian, Dongliang Cao +12Functional MapsNon-Rigid Shape Correspondence

    MPI for Informatics · Imperial College London · Technical University of Munich +5

  29. RINO: Rotation-Invariant Non-Rigid Correspondences

    Mar 29, 2026Maolin Gao, Shao Jie Hu-Chen, Congyue Deng +3Functional MapsNon-Rigid Shape Correspondence

    TUM · MCML · Stanford University +1

  30. From Feature Learning to Spectral Basis Learning: A Unifying and Flexible Framework for Efficient and Robust Shape Matching

    Mar 24, 2026Feifan Luo, Hongyang ChenFunctional MapsNon-Rigid Shape Correspondence

    College of Computer Science and Technology, Zhejiang University, China · Research Center for Computational Earth and Space Science, Zhejiang Lab, China