mlsanityData to 7 Oct 2026

Bending Graphs: Hierarchical Shape Matching using Gated Optimal Transport

arXiv 2202.01537 ↗First posted 3 Feb 2022cs.CV cs.CG cs.GRcited by 24

Not on the map. Why?

Abstract (arXiv)

Shape matching has been a long-studied problem for the computer graphics and vision community. The objective is to predict a dense correspondence between meshes that have a certain degree of deformation. Existing methods either consider the local description of sampled points or discover correspondences based on global shape information. In this work, we investigate a hierarchical learning design, to which we incorporate local patch-level information and global shape-level structures. This flexible representation enables correspondence prediction and provides rich features for the matching stage. Finally, we propose a novel optimal transport solver by recurrently updating features on non-confident nodes to learn globally consistent correspondences between the shapes. Our results on publicly available datasets suggest robust performance in presence of severe deformations without the need for extensive training or refinement.

Key facts. Cited by 24 papers in the map (data through 7 Oct 2026). Builds on 48 of its 79 references that are in the map. First posted on arXiv 3 Feb 2022.

Builds on

48 of 79 references.

References · 48

  1. 2017Attention Is All You Needcited by 59,932
  2. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  3. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  4. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  5. 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,170
  6. 2019SuperGlue: Learning Feature Matching with Graph Neural Networkscited by 1,437
  7. 2014On the Properties of Neural Machine Translation: Encoder-Decoder Approachescited by 1,303
  8. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,202
  9. 2021Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gaugescited by 1,131
  10. 2018Hierarchical Graph Representation Learning with Differentiable Poolingcited by 786
  11. 2018PointCNN: Convolution On X-Transformed Pointscited by 764
  12. 2016Geometric deep learning on graphs and manifolds using mixture model CNNscited by 468
36 more
  1. 2017Scene Graph Generation by Iterative Message Passingcited by 462
  2. 2017Learning from Synthetic Humanscited by 358
  3. 20163DMatch: Learning Local Geometric Descriptors from RGB-D Reconstructionscited by 333
  4. 2019Deep Closest Point: Learning Representations for Point Cloud Registrationcited by 318
  5. 20163D Menagerie: Modeling the 3D shape and pose of animalscited by 310
  6. 2019PointNetLK: Robust & Efficient Point Cloud Registration using PointNetcited by 231
  7. 2015Conditional Random Fields as Recurrent Neural Networkscited by 213
  8. 2020Learning 3D Semantic Scene Graphs from 3D Indoor Reconstructionscited by 205
  9. 2018PPFNet: Global Context Aware Local Features for Robust 3D Point Matchingcited by 180
  10. 2018The Perfect Match: 3D Point Cloud Matching with Smoothed Densitiescited by 169
  11. 20183D-CODED : 3D Correspondences by Deep Deformationcited by 160
  12. 2021SceneGraphFusion: Incremental 3D Scene Graph Prediction from RGB-D Sequencescited by 159
  13. 2021CoFiNet: Reliable Coarse-to-fine Correspondences for Robust Point Cloud Registrationcited by 151
  14. 2017Deep Functional Maps: Structured Prediction for Dense Shape Correspondencecited by 134
  15. 2020FLOT: Scene Flow on Point Clouds Guided by Optimal Transportcited by 129
  16. 2020Deep Geometric Functional Maps: Robust Feature Learning for Shape Correspondencecited by 125
  17. 2017Topology Adaptive Graph Convolutional Networkscited by 112
  18. 2019Three-D Safari: Learning to Estimate Zebra Pose, Shape, and Texture from Images "In the Wild"cited by 106
  19. 2018Towards Sparse Hierarchical Graph Classifierscited by 100
  20. 2019SpiralNet++: A Fast and Highly Efficient Mesh Convolution Operatorcited by 89
  21. 2018Unsupervised Deep Learning for Structured Shape Matchingcited by 81
  22. 2020Faster Wasserstein Distance Estimation with the Sinkhorn Divergencecited by 73
  23. 2018RGCNN: Regularized Graph CNN for Point Cloud Segmentationcited by 70
  24. 2015Partial Functional Correspondencecited by 61
  25. 2021Shape registration in the time of transformerscited by 51
  26. 2020Correspondence Learning via Linearly-invariant Embeddingcited by 48
  27. 2015Building Statistical Shape Spaces for 3D Human Modelingcited by 47
  28. 2017Learning Compact Geometric Featurescited by 45
  29. 2020Latent-Graph Learning for Disease Predictioncited by 39
  30. 2013Rotational Projection Statistics for 3D Local Surface Description and Object Recognitioncited by 36
  31. 2017Product Manifold Filter: Non-Rigid Shape Correspondence via Kernel Density Estimation in the Product Spacecited by 30
  32. 20193D-RelNet: Joint Object and Relational Network for 3D Predictioncited by 28
  33. 2021Distilling Holistic Knowledge with Graph Neural Networkscited by 26
  34. 2020GCNNMatch: Graph Convolutional Neural Networks for Multi-Object Tracking via Sinkhorn Normalizationcited by 25
  35. 2020Graphite: GRAPH-Induced feaTure Extraction for Point Cloud Registrationcited by 12
  36. 2021MIGS: Meta Image Generation from Scene Graphscited by 7

Built on by

Cited by year

Citing papers per year: 2022: 3; 2023: 10; 2024: 6; 2025: 5.

24 papers.

Sort:

By area:

  1. 2023Rotation-Invariant Transformer for Point Cloud Matchingcited by 68
  2. 2023Deformable 3D Gaussian Splatting for Animatable Human Avatarscited by 44
  3. 2022MeshMAE: Masked Autoencoders for 3D Mesh Data Analysiscited by 31
  4. 2022RIGA: Rotation-Invariant and Globally-Aware Descriptors for Point Cloud Registrationcited by 25
  5. 2023Self-Supervised Learning for Multimodal Non-Rigid 3D Shape Matchingcited by 23
  6. 2023CheckerPose: Progressive Dense Keypoint Localization for Object Pose Estimation with Graph Neural Networkcited by 15
  7. 2023Deep Graph-based Spatial Consistency for Robust Non-rigid Point Cloud Registrationcited by 14
  8. 2023S3M: Scalable Statistical Shape Modeling through Unsupervised Correspondencescited by 11
  9. 2023Scalable Unbalanced Sobolev Transport for Measures on a Graphcited by 10
  10. 2023Optimal Transport for Measures with Noisy Tree Metriccited by 7
  11. 2024Unsupervised Cross-Domain Image Retrieval via Prototypical Optimal Transportcited by 7
  12. 2024Tree-Sliced Wasserstein Distance: A Geometric Perspectivecited by 7
12 more
  1. 2024Physics-Encoded Graph Neural Networks for Deformation Prediction under Contactcited by 6
  2. 2024ESCAPE: Equivariant Shape Completion via Anchor Point Encodingcited by 4
  3. 2025Distance-Based Tree-Sliced Wasserstein Distancecited by 4
  4. 2025Efficient Transferable Optimal Transport via Min-Sliced Transport Planscited by 4
  5. 2023Few-Shot Object Detection via Synthetic Features with Optimal Transportcited by 3
  6. 2025Tree-Sliced Wasserstein Distance with Nonlinear Projectioncited by 3
  7. 2022CloudAttention: Efficient Multi-Scale Attention Scheme For 3D Point Cloud Learningcited by 2
  8. 2023Shape-Graph Matching Network (SGM-net): Registration for Statistical Shape Analysiscited by 2
  9. 2025FUSE: A Flow-based Mapping Between Shapescited by 2
  10. 2024SelfGeo: Self-supervised and Geodesic-consistent Estimation of Keypoints on Deformable Shapescited by 1
  11. 2024A Recipe for Geometry-Aware 3D Mesh Transformerscited by 1
  12. 2025Multiview Point Cloud Registration via Optimization in an Autoencoder Latent Spacecited by 1