mlsanityData to 7 Oct 2026

Shape Non-rigid Kinematics (SNK): A Zero-Shot Method for Non-Rigid Shape Matching via Unsupervised Functional Map Regularized Reconstruction

arXiv 2403.06804 ↗First posted 11 Mar 2024cs.CVcited by 7

Not on the map. Why?

Abstract (arXiv)

We present Shape Non-rigid Kinematics (SNK), a novel zero-shot method for non-rigid shape matching that eliminates the need for extensive training or ground truth data. SNK operates on a single pair of shapes, and employs a reconstruction-based strategy using an encoder-decoder architecture, which deforms the source shape to closely match the target shape. During the process, an unsupervised functional map is predicted and converted into a point-to-point map, serving as a supervisory mechanism for the reconstruction. To aid in training, we have designed a new decoder architecture that generates smooth, realistic deformations. SNK demonstrates competitive results on traditional benchmarks, simplifying the shape-matching process without compromising accuracy. Our code can be found online: https://github.com/pvnieo/SNK

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 40 of its 86 references that are in the map. First posted on arXiv 11 Mar 2024.

Builds on

40 of 86 references.

References · 40

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  2. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,682
  3. 2017Deep Image Priorcited by 1,097
  4. 2016Geometric deep learning: going beyond Euclidean datacited by 1,042
  5. 2020Implicit Geometric Regularization for Learning Shapescited by 707
  6. 2019Deep Learning for 3D Point Clouds: A Surveycited by 557
  7. 2016Geometric deep learning on graphs and manifolds using mixture model CNNscited by 468
  8. 20163D Menagerie: Modeling the 3D shape and pose of animalscited by 310
  9. 2018Generating 3D faces using Convolutional Mesh Autoencoderscited by 267
  10. 2020DiffusionNet: Discretization Agnostic Learning on Surfacescited by 163
  11. 20183D-CODED : 3D Correspondences by Deep Deformationcited by 160
  12. 2017Deep Functional Maps: Structured Prediction for Dense Shape Correspondencecited by 134
28 more
  1. 2020Deep Geometric Functional Maps: Robust Feature Learning for Shape Correspondencecited by 125
  2. 2019PointDAN: A Multi-Scale 3D Domain Adaption Network for Point Cloud Representationcited by 114
  3. 20183D Point Capsule Networkscited by 106
  4. 2016Learning shape correspondence with anisotropic convolutional neural networkscited by 95
  5. 2019Neural 3D Morphable Models: Spiral Convolutional Networks for 3D Shape Representation Learning and Generationcited by 89
  6. 2018Unsupervised Deep Learning for Structured Shape Matchingcited by 81
  7. 2021NeuroMorph: Unsupervised Shape Interpolation and Correspondence in One Gocited by 81
  8. 2018Continuous and Orientation-preserving Correspondences via Functional Mapscited by 77
  9. 2020Deep Shells: Unsupervised Shape Correspondence with Optimal Transportcited by 74
  10. 2019Smooth Shells: Multi-Scale Shape Registration with Functional Mapscited by 72
  11. 2015Partial Functional Correspondencecited by 61
  12. 2021DPFM: Deep Partial Functional Mapscited by 58
  13. 2023Unsupervised Learning of Robust Spectral Shape Matchingcited by 57
  14. 2021Shape registration in the time of transformerscited by 51
  15. 2017Deformable Shape Completion with Graph Convolutional Autoencoderscited by 50
  16. 2020Correspondence Learning via Linearly-invariant Embeddingcited by 48
  17. 2015Building Statistical Shape Spaces for 3D Human Modelingcited by 47
  18. 2022Deep Orientation-Aware Functional Maps: Tackling Symmetry Issues in Shape Matchingcited by 36
  19. 2018Multi-directional Geodesic Neural Networks via Equivariant Convolutioncited by 32
  20. 2017Product Manifold Filter: Non-Rigid Shape Correspondence via Kernel Density Estimation in the Product Spacecited by 30
  21. 2019Cyclic Functional Mapping: Self-supervised correspondence between non-isometric deformable shapescited by 30
  22. 2023Spatially and Spectrally Consistent Deep Functional Mapscited by 30
  23. 2023Understanding and Improving Features Learned in Deep Functional Mapscited by 20
  24. 2020Non-Rigid Puzzlescited by 18
  25. 2023NCP: Neural Correspondence Prior for Effective Unsupervised Shape Matchingcited by 18
  26. 2022SRFeat: Learning Locally Accurate and Globally Consistent Non-Rigid Shape Correspondencecited by 13
  27. 2020MapTree: Recovering Multiple Solutions in the Space of Mapscited by 11
  28. 2023Generalizable Local Feature Pre-training for Deformable Shape Analysiscited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 4; 2026: 2.

7 papers.

  1. 2025DiffuMatch: Category-Agnostic Spectral Diffusion Priors for Robust Non-rigid Shape Matchingcited by 10
  2. 2024Synchronous Diffusion for Unsupervised Smooth Non-Rigid 3D Shape Matchingcited by 7
  3. 2025Stable-SCore: A Stable Registration-based Framework for 3D Shape Correspondencecited by 7
  4. 2026RINO: Rotation-Invariant Non-Rigid Correspondencescited by 2
  5. 2025SemMorph3D: Unsupervised Semantic-Aware 3D Morphing via Mesh-Guided Gaussianscited by 1
  6. 2026SGSoft: Learning Fused Semantic-Geometric Features for 3D Shape Correspondence via Template-Guided Soft Signalscited by 1
  7. 2025ScanMove: Motion Prediction and Transfer for Unregistered Body Meshescited by 0