mlsanityData to 7 Oct 2026

Synchronous Diffusion for Unsupervised Smooth Non-Rigid 3D Shape Matching

arXiv 2407.08244 ↗First posted 11 Jul 2024cs.CV cs.CGcited by 7

Not on the map. Why?

Abstract (arXiv)

Most recent unsupervised non-rigid 3D shape matching methods are based on the functional map framework due to its efficiency and superior performance. Nevertheless, respective methods struggle to obtain spatially smooth pointwise correspondences due to the lack of proper regularisation. In this work, inspired by the success of message passing on graphs, we propose a synchronous diffusion process which we use as regularisation to achieve smoothness in non-rigid 3D shape matching problems. The intuition of synchronous diffusion is that diffusing the same input function on two different shapes results in consistent outputs. Using different challenging datasets, we demonstrate that our novel regularisation can substantially improve the state-of-the-art in shape matching, especially in the presence of topological noise.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 62 of its 101 references that are in the map. First posted on arXiv 11 Jul 2024.

Builds on

62 of 101 references.

References · 62

  1. 2017Inductive Representation Learning on Large Graphscited by 6,284
  2. 2018How Powerful are Graph Neural Networks?cited by 4,355
  3. 2017Neural Message Passing for Quantum Chemistrycited by 3,460
  4. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,906
  5. 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,085
  6. 2019SuperGlue: Learning Feature Matching with Graph Neural Networkscited by 1,437
  7. 2018Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networkscited by 878
  8. 2019Diffusion Improves Graph Learningcited by 414
  9. 20163D Menagerie: Modeling the 3D shape and pose of animalscited by 310
  10. 2014Sketching as a Tool for Numerical Linear Algebracited by 285
  11. 20193D Morphable Face Models -- Past, Present and Futurecited by 269
  12. 2020DiffusionNet: Discretization Agnostic Learning on Surfacescited by 163
38 more
  1. 20183D-CODED : 3D Correspondences by Deep Deformationcited by 160
  2. 2017Deep Functional Maps: Structured Prediction for Dense Shape Correspondencecited by 134
  3. 2020Deep Geometric Functional Maps: Robust Feature Learning for Shape Correspondencecited by 125
  4. 20214DComplete: Non-Rigid Motion Estimation Beyond the Observable Surfacecited by 123
  5. 2021Weisfeiler and Leman go Machine Learning: The Story so farcited by 121
  6. 2016Learning Dense Correspondence via 3D-guided Cycle Consistencycited by 91
  7. 2020Deep Graph Matching Consensuscited by 85
  8. 2018Unsupervised Deep Learning for Structured Shape Matchingcited by 81
  9. 2021NeuroMorph: Unsupervised Shape Interpolation and Correspondence in One Gocited by 81
  10. 2018Continuous and Orientation-preserving Correspondences via Functional Mapscited by 77
  11. 2020Deep Shells: Unsupervised Shape Correspondence with Optimal Transportcited by 74
  12. 2019Smooth Shells: Multi-Scale Shape Registration with Functional Mapscited by 72
  13. 2015Partial Functional Correspondencecited by 61
  14. 2022A Survey of Non-Rigid 3D Registrationcited by 59
  15. 2021DPFM: Deep Partial Functional Mapscited by 58
  16. 2023Unsupervised Learning of Robust Spectral Shape Matchingcited by 57
  17. 2021Shape registration in the time of transformerscited by 51
  18. 2022Unsupervised Deep Multi-Shape Matchingcited by 39
  19. 2022Smooth Non-Rigid Shape Matching via Effective Dirichlet Energy Optimizationcited by 37
  20. 2022Deep Orientation-Aware Functional Maps: Tackling Symmetry Issues in Shape Matchingcited by 36
  21. 2022Learning Multi-resolution Functional Maps with Spectral Attention for Robust Shape Matchingcited by 35
  22. 2020Isometric Multi-Shape Matchingcited by 33
  23. 2017Product Manifold Filter: Non-Rigid Shape Correspondence via Kernel Density Estimation in the Product Spacecited by 30
  24. 20213D Pose Transfer with Correspondence Learning and Mesh Refinementcited by 30
  25. 2023Spatially and Spectrally Consistent Deep Functional Mapscited by 30
  26. 2020Structured Regularization of Functional Map Computationscited by 26
  27. 2024Spectral Meets Spatial: Harmonising 3D Shape Matching and Interpolationcited by 26
  28. 2017Efficient Deformable Shape Correspondence via Kernel Matchingcited by 25
  29. 2019Unsupervised cycle-consistent deformation for shape matchingcited by 23
  30. 2023Self-Supervised Learning for Multimodal Non-Rigid 3D Shape Matchingcited by 23
  31. 2022Unsupervised 3D Pose Transfer with Cross Consistency and Dual Reconstructioncited by 21
  32. 2020MINA: Convex Mixed-Integer Programming for Non-Rigid Shape Alignmentcited by 20
  33. 2023Understanding and Improving Features Learned in Deep Functional Mapscited by 20
  34. 2018Reversible Harmonic Maps between Discrete Surfacescited by 19
  35. 2022A Scalable Combinatorial Solver for Elastic Geometrically Consistent 3D Shape Matchingcited by 19
  36. 2021Deep Graph Matching under Quadratic Constraintcited by 18
  37. 2023NCP: Neural Correspondence Prior for Effective Unsupervised Shape Matchingcited by 18
  38. 2022TIDE: Time Derivative Diffusion for Deep Learning on Graphscited by 17

50 most cited of 62 All 62 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 2; 2026: 5.

7 papers.

  1. 2025DiffuMatch: Category-Agnostic Spectral Diffusion Priors for Robust Non-rigid Shape Matchingcited by 10
  2. 2026SGMatch: Semantic-Guided Non-Rigid Shape Matching with Flow Regularizationcited by 2
  3. 2026SGSoft: Learning Fused Semantic-Geometric Features for 3D Shape Correspondence via Template-Guided Soft Signalscited by 1
  4. 2025Sinkhorn Normalization of Diffusion Kernelscited by 0
  5. 2026Auditing Training-Free 3D Shape Retrieval with Diffused Geodesic Momentscited by 0
  6. 2026Geometry-Grounded Articulation and Test-Time Adaptation for Zero-Shot, Scalable Shape Matching in the Wildcited by 0
  7. 2026NHO: A Neural Hamiltonian Operator for Anchor-based Region Localization and Dense Correspondencecited by 0