mlsanityData to 7 Oct 2026

CaDeX: Learning Canonical Deformation Coordinate Space for Dynamic Surface Representation via Neural Homeomorphism

arXiv 2203.16529 ↗First posted 30 Mar 2022cs.CVcited by 56

Not on the map. Why?

Abstract (arXiv)

While neural representations for static 3D shapes are widely studied, representations for deformable surfaces are limited to be template-dependent or lack efficiency. We introduce Canonical Deformation Coordinate Space (CaDeX), a unified representation of both shape and nonrigid motion. Our key insight is the factorization of the deformation between frames by continuous bijective canonical maps (homeomorphisms) and their inverses that go through a learned canonical shape. Our novel deformation representation and its implementation are simple, efficient, and guarantee cycle consistency, topology preservation, and, if needed, volume conservation. Our modelling of the learned canonical shapes provides a flexible and stable space for shape prior learning. We demonstrate state-of-the-art performance in modelling a wide range of deformable geometries: human bodies, animal bodies, and articulated objects.

Key facts. Cited by 56 papers in the map (data through 7 Oct 2026). Builds on 48 of its 61 references that are in the map. First posted on arXiv 30 Mar 2022.

Builds on

48 of 61 references.

References · 48

  1. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  2. 2018Neural Ordinary Differential Equationscited by 3,733
  3. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  4. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,682
  5. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,037
  6. 2016Density estimation using Real NVPcited by 2,029
  7. 2018Glow: Generative Flow with Invertible 1x1 Convolutionscited by 1,539
  8. 2020D-NeRF: Neural Radiance Fields for Dynamic Scenescited by 1,459
  9. 2018Learning Implicit Fields for Generative Shape Modelingcited by 1,060
  10. 2014NICE: Non-linear Independent Components Estimationcited by 1,052
  11. 2016A Point Set Generation Network for 3D Object Reconstruction from a Single Imagecited by 972
  12. 2020Convolutional Occupancy Networkscited by 760
36 more
  1. 2017Masked Autoregressive Flow for Density Estimationcited by 680
  2. 2021UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstructioncited by 643
  3. 2018AtlasNet: A Papier-Mach'e Approach to Learning 3D Surface Generationcited by 539
  4. 2021Neural Fields in Visual Computing and Beyondcited by 539
  5. 2019PointFlow: 3D Point Cloud Generation with Continuous Normalizing Flowscited by 487
  6. 2020Local Implicit Grid Representations for 3D Scenescited by 372
  7. 2018Invertible Residual Networkscited by 364
  8. 2020Implicit Functions in Feature Space for 3D Shape Reconstruction and Completioncited by 343
  9. 2015MADE: Masked Autoencoder for Distribution Estimationcited by 306
  10. 2021SNARF: Differentiable Forward Skinning for Animating Non-Rigid Neural Implicit Shapescited by 221
  11. 2021SCANimate: Weakly Supervised Learning of Skinned Clothed Avatar Networkscited by 181
  12. 2022Embodied Hands: Modeling and Capturing Hands and Bodies Togethercited by 179
  13. 2019NASA: Neural Articulated Shape Approximationcited by 149
  14. 20214DComplete: Non-Rigid Motion Estimation Beyond the Observable Surfacecited by 123
  15. 2020Deformed Implicit Field: Modeling 3D Shapes with Learned Dense Correspondencecited by 119
  16. 2019Shape2Motion: Joint Analysis of Motion Parts and Attributes from 3D Shapescited by 117
  17. 2021A-SDF: Learning Disentangled Signed Distance Functions for Articulated Shape Representationcited by 113
  18. 2020i3DMM: Deep Implicit 3D Morphable Model of Human Headscited by 109
  19. 2021Neural-GIF: Neural Generalized Implicit Functions for Animating People in Clothingcited by 102
  20. 2021Neural Parts: Learning Expressive 3D Shape Abstractions with Invertible Neural Networkscited by 101
  21. 2021NPMs: Neural Parametric Models for 3D Deformable Shapescited by 89
  22. 2020Deep Implicit Templates for 3D Shape Representationcited by 86
  23. 2021MetaAvatar: Learning Animatable Clothed Human Models from Few Depth Imagescited by 78
  24. 2020Neural Deformation Graphs for Globally-consistent Non-rigid Reconstructioncited by 66
  25. 2020Neural Mesh Flow: 3D Manifold Mesh Generation via Diffeomorphic Flowscited by 60
  26. 2020CaSPR: Learning Canonical Spatiotemporal Point Cloud Representationscited by 51
  27. 2021A Skeleton-Driven Neural Occupancy Representation for Articulated Handscited by 50
  28. 2021GarmentNets: Category-Level Pose Estimation for Garments via Canonical Space Shape Completioncited by 41
  29. 2020Learning 3D Dynamic Scene Representations for Robot Manipulationcited by 39
  30. 2021Video Autoencoder: self-supervised disentanglement of static 3D structure and motioncited by 34
  31. 2021Learning Parallel Dense Correspondence from Spatio-Temporal Descriptors for Efficient and Robust 4D Reconstructioncited by 31
  32. 2020ShapeFlow: Learnable Deformations Among 3D Shapescited by 28
  33. 2021Learning Compositional Representation for 4D Captures with Neural ODEcited by 22
  34. 2019Local Deep Implicit Functions for 3D Shapecited by 18
  35. 2021Temporally-Coherent Surface Reconstruction via Metric-Consistent Atlasescited by 7
  36. 2020MeshODE: A Robust and Scalable Framework for Mesh Deformationcited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 5; 2023: 19; 2024: 21; 2025: 5; 2026: 6.

56 papers.

Sort:

By area:

  1. 2023Tracking Everything Everywhere All at Oncecited by 190
  2. 2024SpatialTracker: Tracking Any 2D Pixels in 3D Spacecited by 178
  3. 2023CARTO: Category and Joint Agnostic Reconstruction of ARTiculated Objectscited by 64
  4. 2022Neural Surface Reconstruction of Dynamic Scenes with Monocular RGB-D Cameracited by 57
  5. 2024MoDGS: Dynamic Gaussian Splatting from Casually-captured Monocular Videos with Depth Priorscited by 51
  6. 2023Reconstructing Animatable Categories from Videoscited by 46
  7. 2024REACTO: Reconstructing Articulated Objects from a Single Videocited by 45
  8. 2023Flow supervision for Deformable NeRFcited by 42
  9. 2025PhysCtrl: Generative Physics for Controllable and Physics-Grounded Video Generationcited by 39
  10. 2023Dynamic Point Fieldscited by 37
  11. 2022CASA: Category-agnostic Skeletal Animal Reconstructioncited by 35
  12. 2023MonoNPHM: Dynamic Head Reconstruction from Monocular Videoscited by 35
38 more
  1. 2022K-VIL: Keypoints-based Visual Imitation Learningcited by 27
  2. 2024Motion2VecSets: 4D Latent Vector Set Diffusion for Non-rigid Shape Reconstruction and Trackingcited by 27
  3. 2023NAP: Neural 3D Articulation Priorcited by 25
  4. 2023Banana: Banach Fixed-Point Network for Pointcloud Segmentation with Inter-Part Equivariancecited by 19
  5. 2023EFEM: Equivariant Neural Field Expectation Maximization for 3D Object Segmentation Without Scene Supervisioncited by 18
  6. 2024Diffusion Priors for Dynamic View Synthesis from Monocular Videoscited by 18
  7. 2024LEIA: Latent View-invariant Embeddings for Implicit 3D Articulationcited by 16
  8. 2023Relightable and Animatable Neural Avatars from Videoscited by 13
  9. 2024Track Everything Everywhere Fast and Robustlycited by 13
  10. 2023Zero-shot Pose Transfer for Unrigged Stylized 3D Characterscited by 12
  11. 2022Neural Vector Fields for Implicit Surface Representation and Inferencecited by 10
  12. 2023DPHMs: Diffusion Parametric Head Models for Depth-based Trackingcited by 10
  13. 2023textttNePhi: Neural Deformation Fields for Approximately Diffeomorphic Medical Image Registrationcited by 8
  14. 2024DynoSurf: Neural Deformation-based Temporally Consistent Dynamic Surface Reconstructioncited by 8
  15. 2024OP-Align: Object-level and Part-level Alignment for Self-supervised Category-level Articulated Object Pose Estimationcited by 8
  16. 2023NAISR: A 3D Neural Additive Model for Interpretable Shape Representationcited by 7
  17. 2023Fluid Dynamics Network: Topology-Agnostic 4D Reconstruction via Fluid Dynamics Priorscited by 7
  18. 2024Dynamic 3D Point Cloud Sequences as 2D Videoscited by 7
  19. 2024CanFields: Consolidating Diffeomorphic Flows for Non-Rigid 4D Interpolation from Arbitrary-Length Sequencescited by 6
  20. 2023Dyn-E: Local Appearance Editing of Dynamic Neural Radiance Fieldscited by 5
  21. 2024Invertible Neural Warp for NeRFcited by 5
  22. 2022KiloNeuS: A Versatile Neural Implicit Surface Representation for Real-Time Renderingcited by 4
  23. 2023Fast Point Cloud to Mesh Reconstruction for Deformable Object Trackingcited by 4
  24. 2024Learning Coherent Matrixized Representation in Latent Space for Volumetric 4D Generationcited by 4
  25. 2024PokeFlex: A Real-World Dataset of Volumetric Deformable Objects for Roboticscited by 4
  26. 2023Semantic-Aware Implicit Template Learning via Part Deformation Consistencycited by 3
  27. 2024TutteNet: Injective 3D Deformations by Composition of 2D Mesh Deformationscited by 3
  28. 2024Equivariant Local Reference Frames for Unsupervised Non-rigid Point Cloud Shape Correspondencecited by 2
  29. 2024Self-supervised Shape Completion via Involution and Implicit Correspondencescited by 2
  30. 2024TFS-NeRF: Template-Free NeRF for Semantic 3D Reconstruction of Dynamic Scenecited by 2
  31. 2025FOLIAGE: Towards Physical Intelligence World Models Via Unbounded Surface Evolutioncited by 2
  32. 2025Advances and Trends in the 3D Reconstruction of the Shape and Motion of Animalscited by 2
  33. 2023Invertible Neural Skinningcited by 1
  34. 2024SPARE: Symmetrized Point-to-Plane Distance for Robust Non-Rigid 3D Registrationcited by 1
  35. 2025Preconditioned Deformation Gridscited by 1
  36. 2025ERNet: Efficient Non-Rigid Registration Network for Point Sequencescited by 1
  37. 2026Discovering Data Manifold Geometry through Geometric Propertiescited by 1
  38. 2026Neu-PiG: Neural Preconditioned Grids for Fast Dynamic Surface Reconstruction on Long Sequencescited by 1

50 most cited of 56 All 56 (JSON)