mlsanityData to 14 Oct 2026

DynoSurf: Neural Deformation-based Temporally Consistent Dynamic Surface Reconstruction

arXiv 2403.11586 ↗First posted 18 Mar 2024cs.CVcited by 8

Not on the map. Why?

Abstract (arXiv)

This paper explores the problem of reconstructing temporally consistent surfaces from a 3D point cloud sequence without correspondence. To address this challenging task, we propose DynoSurf, an unsupervised learning framework integrating a template surface representation with a learnable deformation field. Specifically, we design a coarse-to-fine strategy for learning the template surface based on the deformable tetrahedron representation. Furthermore, we propose a learnable deformation representation based on the learnable control points and blending weights, which can deform the template surface non-rigidly while maintaining the consistency of the local shape. Experimental results demonstrate the significant superiority of DynoSurf over current state-of-the-art approaches, showcasing its potential as a powerful tool for dynamic mesh reconstruction. The code is publicly available at https://github.com/yaoyx689/DynoSurf.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 42 of its 65 references that are in the map. First posted on arXiv 18 Mar 2024.

Builds on

42 of 65 references.

References · 42

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  3. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  4. 2018Neural Ordinary Differential Equationscited by 3,779
  5. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,689
  6. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,041
  7. 2018On the Spectral Bias of Neural Networkscited by 1,341
  8. 2020Nerfies: Deformable Neural Radiance Fieldscited by 1,198
  9. 2018PointCNN: Convolution On X-Transformed Pointscited by 764
  10. 2020Convolutional Occupancy Networkscited by 761
  11. 2020Non-Rigid Neural Radiance Fields: Reconstruction and Novel View Synthesis of a Dynamic Scene From Monocular Videocited by 471
  12. 2021Deep Marching Tetrahedra: a Hybrid Representation for High-Resolution 3D Shape Synthesiscited by 460
30 more
  1. 2019SAL: Sign Agnostic Learning of Shapes from Raw Datacited by 390
  2. 20163DMatch: Learning Local Geometric Descriptors from RGB-D Reconstructionscited by 336
  3. 20163D Menagerie: Modeling the 3D shape and pose of animalscited by 312
  4. 2018FlowNet3D: Learning Scene Flow in 3D Point Cloudscited by 242
  5. 2021Shape As Points: A Differentiable Poisson Solvercited by 187
  6. 2023Flexible Isosurface Extraction for Gradient-Based Mesh Optimizationcited by 139
  7. 20214DComplete: Non-Rigid Motion Estimation Beyond the Observable Surfacecited by 124
  8. 2020i3DMM: Deep Implicit 3D Morphable Model of Human Headscited by 109
  9. 2023Neural Kernel Surface Reconstructioncited by 104
  10. 2018MeshNet: Mesh Neural Network for 3D Shape Representationcited by 95
  11. 2022POCO: Point Convolution for Surface Reconstructioncited by 92
  12. 2021NPMs: Neural Parametric Models for 3D Deformable Shapescited by 90
  13. 2020Neural Deformation Graphs for Globally-consistent Non-rigid Reconstructioncited by 67
  14. 2021Deep Implicit Moving Least-Squares Functions for 3D Reconstructioncited by 67
  15. 2022CaDeX: Learning Canonical Deformation Coordinate Space for Dynamic Surface Representation via Neural Homeomorphismcited by 57
  16. 2020CaSPR: Learning Canonical Spatiotemporal Point Cloud Representationscited by 51
  17. 2020CorrNet3D: Unsupervised End-to-end Learning of Dense Correspondence for 3D Point Cloudscited by 47
  18. 2021GarmentNets: Category-Level Pose Estimation for Garments via Canonical Space Shape Completioncited by 43
  19. 2022Non-rigid Point Cloud Registration with Neural Deformation Pyramidcited by 42
  20. 2021Learning Parallel Dense Correspondence from Spatio-Temporal Descriptors for Efficient and Robust 4D Reconstructioncited by 31
  21. 2022GeoUDF: Surface Reconstruction from 3D Point Clouds via Geometry-guided Distance Representationcited by 29
  22. 2020Recurrent Multi-view Alignment Network for Unsupervised Surface Registrationcited by 19
  23. 2020Quasi-Newton Solver for Robust Non-Rigid Registrationcited by 17
  24. 2022H4D: Human 4D Modeling by Learning Neural Compositional Representationcited by 15
  25. 2022Fast and Robust Non-Rigid Registration Using Accelerated Majorization-Minimizationcited by 12
  26. 2019DispVoxNets: Non-Rigid Point Set Alignment with Supervised Learning Proxiescited by 8
  27. 2022LoRD: Local 4D Implicit Representation for High-Fidelity Dynamic Human Modelingcited by 8
  28. 2023Self-supervised Learning of Implicit Shape Representation with Dense Correspondence for Deformable Objectscited by 8
  29. 2023Fluid Dynamics Network: Topology-Agnostic 4D Reconstruction via Fluid Dynamics Priorscited by 7
  30. 2022IPNET:Influential Prototypical Networks for Few Shot Learningcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 6; 2026: 1.

8 papers.

  1. 2025RigGS: Rigging of 3D Gaussians for Modeling Articulated Objects in Videoscited by 14
  2. 2025FreeGave: 3D Physics Learning from Dynamic Videos by Gaussian Velocitycited by 13
  3. 2025Learning Bijective Surface Parameterization for Inferring Signed Distance Functions from Sparse Point Clouds with Grid Deformationcited by 7
  4. 2025Advances in 4D Representation: Geometry, Motion, and Interactioncited by 4
  5. 2024SPARE: Symmetrized Point-to-Plane Distance for Robust Non-Rigid 3D Registrationcited by 1
  6. 2025Preconditioned Deformation Gridscited by 1
  7. 2025Tessellation GS: Neural Mesh Gaussians for Robust Monocular Reconstruction of Dynamic Objectscited by 1
  8. 2026Neu-PiG: Neural Preconditioned Grids for Fast Dynamic Surface Reconstruction on Long Sequencescited by 1