mlsanityData to 7 Oct 2026

Implicit field supervision for robust non-rigid shape matching

arXiv 2203.07694 ↗First posted 15 Mar 2022cs.CVcited by 13

Not on the map. Why?

Abstract (arXiv)

Establishing a correspondence between two non-rigidly deforming shapes is one of the most fundamental problems in visual computing. Existing methods often show weak resilience when presented with challenges innate to real-world data such as noise, outliers, self-occlusion etc. On the other hand, auto-decoders have demonstrated strong expressive power in learning geometrically meaningful latent embeddings. However, their use in shape analysis has been limited. In this paper, we introduce an approach based on an auto-decoder framework, that learns a continuous shape-wise deformation field over a fixed template. By supervising the deformation field for points on-surface and regularising for points off-surface through a novel Signed Distance Regularisation (SDR), we learn an alignment between the template and shape volumes. Trained on clean water-tight meshes, without any data-augmentation, we demonstrate compelling performance on compromised data and real-world scans.

Key facts. Cited by 13 papers in the map (data through 7 Oct 2026). Builds on 54 of its 89 references that are in the map. First posted on arXiv 15 Mar 2022.

Builds on

54 of 89 references.

References · 54

  1. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,682
  2. 2020Implicit Neural Representations with Periodic Activation Functionscited by 2,214
  3. 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,170
  4. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,037
  5. 2018Learning Implicit Fields for Generative Shape Modelingcited by 1,060
  6. 2017End-to-end Recovery of Human Shape and Posecited by 883
  7. 2019Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representationscited by 864
  8. 2020GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fieldscited by 784
  9. 2020GRAF: Generative Radiance Fields for 3D-Aware Image Synthesiscited by 688
  10. 2018DensePose: Dense Human Pose Estimation In The Wildcited by 573
  11. 2021Neural Fields in Visual Computing and Beyondcited by 539
  12. 2018Simple Baselines for Human Pose Estimation and Trackingcited by 502
38 more
  1. 2016Geometric deep learning on graphs and manifolds using mixture model CNNscited by 468
  2. 2021Neural Geometric Level of Detail: Real-time Rendering with Implicit 3D Shapescited by 426
  3. 2019SAL: Sign Agnostic Learning of Shapes from Raw Datacited by 389
  4. 2017Learning from Synthetic Humanscited by 358
  5. 20163D Menagerie: Modeling the 3D shape and pose of animalscited by 310
  6. 2019Learning Shape Templates with Structured Implicit Functionscited by 242
  7. 2018Neural Body Fitting: Unifying Deep Learning and Model-Based Human Pose and Shape Estimationcited by 185
  8. 2019DIST: Rendering Deep Implicit Signed Distance Function with Differentiable Sphere Tracingcited by 179
  9. 2016Panoptic Studio: A Massively Multiview System for Social Interaction Capturecited by 173
  10. 2020DiffusionNet: Discretization Agnostic Learning on Surfacescited by 163
  11. 20183D-CODED : 3D Correspondences by Deep Deformationcited by 160
  12. 2021SMPLicit: Topology-aware Generative Model for Clothed Peoplecited by 154
  13. 2017Deep Functional Maps: Structured Prediction for Dense Shape Correspondencecited by 134
  14. 2020Deep Geometric Functional Maps: Robust Feature Learning for Shape Correspondencecited by 125
  15. 20214DComplete: Non-Rigid Motion Estimation Beyond the Observable Surfacecited by 123
  16. 2020Deformed Implicit Field: Modeling 3D Shapes with Learned Dense Correspondencecited by 119
  17. 2019PQ-NET: A Generative Part Seq2Seq Network for 3D Shapescited by 118
  18. 2019SDM-NET: Deep Generative Network for Structured Deformable Meshcited by 113
  19. 2020LoopReg: Self-supervised Learning of Implicit Surface Correspondences, Pose and Shape for 3D Human Mesh Registrationcited by 108
  20. 2021Neural-GIF: Neural Generalized Implicit Functions for Animating People in Clothingcited by 102
  21. 2019Learning elementary structures for 3D shape generation and matchingcited by 98
  22. 2016Learning shape correspondence with anisotropic convolutional neural networkscited by 95
  23. 2020Deep Implicit Templates for 3D Shape Representationcited by 86
  24. 2020DualSDF: Semantic Shape Manipulation using a Two-Level Representationcited by 82
  25. 2018Unsupervised Deep Learning for Structured Shape Matchingcited by 81
  26. 2021NeuroMorph: Unsupervised Shape Interpolation and Correspondence in One Gocited by 81
  27. 2018Continuous and Orientation-preserving Correspondences via Functional Mapscited by 77
  28. 2020Deep Shells: Unsupervised Shape Correspondence with Optimal Transportcited by 74
  29. 2019Smooth Shells: Multi-Scale Shape Registration with Functional Mapscited by 72
  30. 2020Learning Unsupervised Hierarchical Part Decomposition of 3D Objects from a Single RGB Imagecited by 72
  31. 20193DN: 3D Deformation Networkcited by 60
  32. 2020Correspondence Learning via Linearly-invariant Embeddingcited by 48
  33. 2020CorrNet3D: Unsupervised End-to-end Learning of Dense Correspondence for 3D Point Cloudscited by 47
  34. 2019Synthetic Humans for Action Recognition from Unseen Viewpointscited by 46
  35. 2020CNNs on Surfaces using Rotation-Equivariant Featurescited by 42
  36. 2019SimulCap : Single-View Human Performance Capture with Cloth Simulationcited by 41
  37. 2020Dual Geometric Graph Network (DG2N) -- Iterative network for deformable shape alignmentcited by 35
  38. 2018Multi-directional Geodesic Neural Networks via Equivariant Convolutioncited by 32

50 most cited of 54 All 54 (JSON)

Built on by

Cited by year

Citing papers per year: 2023: 8; 2024: 2; 2025: 3.

13 papers.

Sort:

By area:

  1. 2024Spectral Meets Spatial: Harmonising 3D Shape Matching and Interpolationcited by 26
  2. 2023Self-Supervised Learning for Multimodal Non-Rigid 3D Shape Matchingcited by 23
  3. 2023SE-ORNet: Self-Ensembling Orientation-aware Network for Unsupervised Point Cloud Shape Correspondencecited by 19
  4. 2025Denoising Functional Maps: Diffusion Models for Shape Correspondencecited by 14
  5. 2023Zero-shot Pose Transfer for Unrigged Stylized 3D Characterscited by 12
  6. 2023CCuantuMM: Cycle-Consistent Quantum-Hybrid Matching of Multiple Shapescited by 11
  7. 2023GenCorres: Consistent Shape Matching via Coupled Implicit-Explicit Shape Generative Modelscited by 11
  8. 2023Self-supervised Learning of Implicit Shape Representation with Dense Correspondence for Deformable Objectscited by 8
  9. 2024Unsupervised Template-assisted Point Cloud Shape Correspondence Networkcited by 7
  10. 2023Kissing to Find a Match: Efficient Low-Rank Permutation Representationcited by 5
  11. 2025Occlusion-aware Non-Rigid Point Cloud Registration via Unsupervised Neural Deformation Correntropycited by 4
  12. 2023Semantic-Aware Implicit Template Learning via Part Deformation Consistencycited by 3
1 more
  1. 2025Matching Shapes Under Different Topologies: A Topology-Adaptive Deformation Guided Approachcited by 0