mlsanityData to 7 Oct 2026

RINO: Rotation-Invariant Non-Rigid Correspondences

arXiv 2603.27773 ↗First posted 29 Mar 2026cs.CVcited by 2

Not on the map. Why?

Abstract (arXiv)

Dense 3D shape correspondence remains a central challenge in computer vision and graphics as many deep learning approaches still rely on intermediate geometric features or handcrafted descriptors, limiting their effectiveness under non-isometric deformations, partial data, and non-manifold inputs. To overcome these issues, we introduce RINO, an unsupervised, rotation-invariant dense correspondence framework that effectively unifies rigid and non-rigid shape matching. The core of our method is the novel RINONet, a feature extractor that integrates vector-based SO(3)-invariant learning with orientation-aware complex functional maps to extract robust features directly from raw geometry. This allows for a fully end-to-end, data-driven approach that bypasses the need for shape pre-alignment or handcrafted features. Extensive experiments show unprecedented performance of RINO across challenging non-rigid matching tasks, including arbitrary poses, non-isometry, partiality, non-manifoldness, and noise.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 43 of its 70 references that are in the map. First posted on arXiv 29 Mar 2026.

Builds on

43 of 70 references.

References · 43

  1. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  2. 2016Group Equivariant Convolutional Networkscited by 1,154
  3. 2016Geometric deep learning: going beyond Euclidean datacited by 1,042
  4. 2018Tensor field networks: Rotation- and translation-equivariant neural networks for 3D point cloudscited by 735
  5. 20163D Menagerie: Modeling the 3D shape and pose of animalscited by 310
  6. 2021Vector Neurons: A General Framework for SO(3)-Equivariant Networkscited by 304
  7. 2022e3nn: Euclidean Neural Networkscited by 171
  8. 2020DiffusionNet: Discretization Agnostic Learning on Surfacescited by 163
  9. 2017Deep Functional Maps: Structured Prediction for Dense Shape Correspondencecited by 134
  10. 2020Deep Geometric Functional Maps: Robust Feature Learning for Shape Correspondencecited by 125
  11. 2020Gauge Equivariant Mesh CNNs: Anisotropic convolutions on geometric graphscited by 90
  12. 2018Unsupervised Deep Learning for Structured Shape Matchingcited by 81
31 more
  1. 2021Equivariant Point Network for 3D Point Cloud Analysiscited by 81
  2. 2018Continuous and Orientation-preserving Correspondences via Functional Mapscited by 77
  3. 2021DPFM: Deep Partial Functional Mapscited by 58
  4. 2019Effective Rotation-invariant Point CNN with Spherical Harmonics kernelscited by 57
  5. 2023Unsupervised Learning of Robust Spectral Shape Matchingcited by 57
  6. 2023Diffusion 3D Features (Diff3F): Decorating Untextured Shapes with Distilled Semantic Featurescited by 55
  7. 2020Correspondence Learning via Linearly-invariant Embeddingcited by 48
  8. 2022Unsupervised Deep Multi-Shape Matchingcited by 39
  9. 2022Smooth Non-Rigid Shape Matching via Effective Dirichlet Energy Optimizationcited by 37
  10. 2022Deep Orientation-Aware Functional Maps: Tackling Symmetry Issues in Shape Matchingcited by 36
  11. 2020Isometric Multi-Shape Matchingcited by 33
  12. 2023Spatially and Spectrally Consistent Deep Functional Mapscited by 30
  13. 2020Structured Regularization of Functional Map Computationscited by 26
  14. 2024Spectral Meets Spatial: Harmonising 3D Shape Matching and Interpolationcited by 26
  15. 2017Efficient Deformable Shape Correspondence via Kernel Matchingcited by 25
  16. 2023Understanding and Improving Features Learned in Deep Functional Mapscited by 20
  17. 2023NCP: Neural Correspondence Prior for Effective Unsupervised Shape Matchingcited by 18
  18. 2023Hybrid Functional Maps for Crease-Aware Non-Isometric Shape Matchingcited by 18
  19. 2021Complex Functional Maps : a Conformal Link Between Tangent Bundlescited by 17
  20. 2024Partial-to-Partial Shape Matching with Geometric Consistencycited by 16
  21. 2024Memory-Scalable and Simplified Functional Map Learningcited by 14
  22. 2023Geometrically Consistent Partial Shape Matchingcited by 13
  23. 2024Integrating Efficient Optimal Transport and Functional Maps For Unsupervised Shape Correspondence Learningcited by 12
  24. 2024DV-Matcher: Deformation-based Non-Rigid Point Cloud Matching Guided by Pre-trained Visual Featurescited by 10
  25. 2025DiffuMatch: Category-Agnostic Spectral Diffusion Priors for Robust Non-rigid Shape Matchingcited by 10
  26. 2023Neural Intrinsic Embedding for Non-rigid Point Cloud Matchingcited by 9
  27. 2023Revisiting Map Relations for Unsupervised Non-Rigid Shape Matchingcited by 8
  28. 2023Multi-body SE(3) Equivariance for Unsupervised Rigid Segmentation and Motion Estimationcited by 7
  29. 2024Shape Non-rigid Kinematics (SNK): A Zero-Shot Method for Non-Rigid Shape Matching via Unsupervised Functional Map Regularized Reconstructioncited by 7
  30. 2025PoissonNet: A Local-Global Approach for Learning on Surfacescited by 6
  31. 2024Learning SO(3)-Invariant Semantic Correspondence via Local Shape Transformcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Ordered Diffusion for 3D Human Registrationcited by 1
  2. 2026MeshLoom: Feed-Forward Non-Rigid Registration of Mesh Sequencescited by 0