mlsanityData to 7 Oct 2026

CanFields: Consolidating Diffeomorphic Flows for Non-Rigid 4D Interpolation from Arbitrary-Length Sequences

arXiv 2406.18582 ↗First posted 5 Jun 2024cs.CV cs.GRcited by 6

Not on the map. Why?

Abstract (arXiv)

We introduce Canonical Consolidation Fields (CanFields). This novel method interpolates arbitrary-length sequences of independently sampled 3D point clouds into a unified, continuous, and coherent deforming shape. Unlike prior methods that oversmooth geometry or produce topological and geometric artifacts, CanFields optimizes fine-detailed geometry and deformation jointly in an unsupervised fitting with two novel bespoke modules. First, we introduce a dynamic consolidator module that adjusts the input and assigns confidence scores, balancing the optimization of the canonical shape and its motion. Second, we represent the motion as a diffeomorphic flow parameterized by a smooth velocity field. We have validated our robustness and accuracy on more than 50 diverse sequences, demonstrating its superior performance even with missing regions, noisy raw scans, and sparse data. Our project page is at: https://wangmiaowei.github.io/CanFields.github.io/.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 56 of its 107 references that are in the map. First posted on arXiv 5 Jun 2024.

Builds on

56 of 107 references.

References · 56

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  2. 2018Neural Ordinary Differential Equationscited by 3,733
  3. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,698
  4. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,682
  5. 2020Implicit Neural Representations with Periodic Activation Functionscited by 2,214
  6. 2020D-NeRF: Neural Radiance Fields for Dynamic Scenescited by 1,459
  7. 2019Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regressioncited by 1,361
  8. 2020Nerfies: Deformable Neural Radiance Fieldscited by 1,194
  9. 2016A Point Set Generation Network for 3D Object Reconstruction from a Single Imagecited by 972
  10. 2023Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene Reconstructioncited by 753
  11. 2020Neural Scene Flow Fields for Space-Time View Synthesis of Dynamic Scenescited by 750
  12. 2023HexPlane: A Fast Representation for Dynamic Scenescited by 582
38 more
  1. 20233DShape2VecSet: A 3D Shape Representation for Neural Fields and Generative Diffusion Modelscited by 449
  2. 2020Space-time Neural Irradiance Fields for Free-Viewpoint Videocited by 414
  3. 2019SAL: Sign Agnostic Learning of Shapes from Raw Datacited by 389
  4. 20223D Neural Field Generation using Triplane Diffusioncited by 274
  5. 2023Gaussian-Flow: 4D Reconstruction with Dynamic 3D Gaussian Particlecited by 210
  6. 2016Thingi10K: A Dataset of 10,000 3D-Printing Modelscited by 182
  7. 2021SCANimate: Weakly Supervised Learning of Skinned Clothed Avatar Networkscited by 181
  8. 20183D-CODED : 3D Correspondences by Deep Deformationcited by 160
  9. 20214DComplete: Non-Rigid Motion Estimation Beyond the Observable Surfacecited by 123
  10. 2020Deformed Implicit Field: Modeling 3D Shapes with Learned Dense Correspondencecited by 119
  11. 2023Neural Kernel Surface Reconstructioncited by 102
  12. 2017Detailed, accurate, human shape estimation from clothed 3D scan sequencescited by 89
  13. 2022Learning Smooth Neural Functions via Lipschitz Regularizationcited by 86
  14. 20233D Registration with Maximal Cliquescited by 83
  15. 2021NeuroMorph: Unsupervised Shape Interpolation and Correspondence in One Gocited by 81
  16. 2021DiGS : Divergence guided shape implicit neural representation for unoriented point cloudscited by 76
  17. 2023Unsupervised Learning of Robust Spectral Shape Matchingcited by 57
  18. 2022CaDeX: Learning Canonical Deformation Coordinate Space for Dynamic Surface Representation via Neural Homeomorphismcited by 56
  19. 2020Neural Splines: Fitting 3D Surfaces with Infinitely-Wide Neural Networkscited by 52
  20. 2022Topology-Preserving Shape Reconstruction and Registration via Neural Diffeomorphic Flowcited by 38
  21. 2023Globally Consistent Normal Orientation for Point Clouds by Regularizing the Winding-Number Fieldcited by 37
  22. 2021Multiresolution Deep Implicit Functions for 3D Shape Representationcited by 35
  23. 2022LiDARCap: Long-range Marker-less 3D Human Motion Capture with LiDAR Point Cloudscited by 32
  24. 2021Learning Parallel Dense Correspondence from Spatio-Temporal Descriptors for Efficient and Robust 4D Reconstructioncited by 31
  25. 2022Consistent 3D Hand Reconstruction in Video via self-supervised Learningcited by 28
  26. 2023NVFi: Neural Velocity Fields for 3D Physics Learning from Dynamic Videoscited by 28
  27. 2024Motion2VecSets: 4D Latent Vector Set Diffusion for Non-rigid Shape Reconstruction and Trackingcited by 27
  28. 2024Spectral Meets Spatial: Harmonising 3D Shape Matching and Interpolationcited by 26
  29. 2022Unbiased 4D: Monocular 4D Reconstruction with a Neural Deformation Modelcited by 25
  30. 2021Learning Compositional Representation for 4D Captures with Neural ODEcited by 22
  31. 2016Temporally coherent 4D reconstruction of complex dynamic scenescited by 21
  32. 2020Kernel-Based Smoothness Analysis of Residual Networkscited by 19
  33. 2021Augmenting Implicit Neural Shape Representations with Explicit Deformation Fieldscited by 19
  34. 2022Neural Implicit Surface Evolutioncited by 18
  35. 2023EXIM: A Hybrid Explicit-Implicit Representation for Text-Guided 3D Shape Generationcited by 16
  36. 2023GenCorres: Consistent Shape Matching via Coupled Implicit-Explicit Shape Generative Modelscited by 11
  37. 2023SceNeRFlow: Time-Consistent Reconstruction of General Dynamic Scenescited by 11
  38. 2023Explicit Neural Surfaces: Learning Continuous Geometry With Deformation Fieldscited by 10

50 most cited of 56 All 56 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 6.

6 papers.

  1. 2026Molecular Representations in Implicit Functional Space via Hyper-Networkscited by 5
  2. 2026BiMotion: B-spline Motion for Text-guided Dynamic 3D Character Generationcited by 4
  3. 2026DynaTok: Token-Based 4D Reconstruction from Partial Point Cloudscited by 0
  4. 2026GrowFields: Compositional 4D Neural Fields for Topology-Changing Plant Growthcited by 0
  5. 2026Low-Rank Velocity Fields as a Structural Prior for Unsupervised 4D Medical Image Interpolationcited by 0
  6. 2026Phase-Aligned Finite-Fourier Periodic Deformation for 4D Medical Image Interpolationcited by 0