mlsanityData to 14 Oct 2026

LoRD: Local 4D Implicit Representation for High-Fidelity Dynamic Human Modeling

arXiv 2208.08622 ↗First posted 18 Aug 2022cs.CVcited by 8

Not on the map. Why?

Abstract (arXiv)

Recent progress in 4D implicit representation focuses on globally controlling the shape and motion with low dimensional latent vectors, which is prone to missing surface details and accumulating tracking error. While many deep local representations have shown promising results for 3D shape modeling, their 4D counterpart does not exist yet. In this paper, we fill this blank by proposing a novel Local 4D implicit Representation for Dynamic clothed human, named LoRD, which has the merits of both 4D human modeling and local representation, and enables high-fidelity reconstruction with detailed surface deformations, such as clothing wrinkles. Particularly, our key insight is to encourage the network to learn the latent codes of local part-level representation, capable of explaining the local geometry and temporal deformations. To make the inference at test-time, we first estimate the inner body skeleton motion to track local parts at each time step, and then optimize the latent codes for each part via auto-decoding based on different types of observed data. Extensive experiments demonstrate that the proposed method has strong capability for representing 4D human, and outperforms state-of-the-art methods on practical applications, including 4D reconstruction from sparse points, non-rigid depth fusion, both qualitatively and quantitatively.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 54 of its 80 references that are in the map. First posted on arXiv 18 Aug 2022.

Builds on

54 of 80 references.

References · 54

  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. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,689
  4. 2020RAFT: Recurrent All-Pairs Field Transforms for Optical Flowcited by 2,415
  5. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,041
  6. 2021NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstructioncited by 1,712
  7. 2020D-NeRF: Neural Radiance Fields for Dynamic Scenescited by 1,465
  8. 2018Learning Implicit Fields for Generative Shape Modelingcited by 1,060
  9. 2021Volume Rendering of Neural Implicit Surfacescited by 996
  10. 2016A Point Set Generation Network for 3D Object Reconstruction from a Single Imagecited by 979
  11. 2019PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitizationcited by 818
  12. 2020Convolutional Occupancy Networkscited by 761
38 more
  1. 2020Implicit Geometric Regularization for Learning Shapescited by 710
  2. 2018Pixel2Mesh: Generating 3D Mesh Models from Single RGB Imagescited by 651
  3. 2017Frustum PointNets for 3D Object Detection from RGB-D Datacited by 640
  4. 2020Neural Body: Implicit Neural Representations with Structured Latent Codes for Novel View Synthesis of Dynamic Humanscited by 634
  5. 2019VIBE: Video Inference for Human Body Pose and Shape Estimationcited by 620
  6. 20163D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstructioncited by 588
  7. 2021Neural Geometric Level of Detail: Real-time Rendering with Implicit 3D Shapescited by 426
  8. 2020Local Implicit Grid Representations for 3D Scenescited by 373
  9. 2020Implicit Functions in Feature Space for 3D Shape Reconstruction and Completioncited by 343
  10. 2020Deep Local Shapes: Learning Local SDF Priors for Detailed 3D Reconstructioncited by 321
  11. 2018Learning Category-Specific Mesh Reconstruction from Image Collectionscited by 317
  12. 2018Learning 3D Human Dynamics from Videocited by 316
  13. 2021Mixture of Volumetric Primitives for Efficient Neural Renderingcited by 277
  14. 2018FlowNet3D: Learning Scene Flow in 3D Point Cloudscited by 242
  15. 2020PaMIR: Parametric Model-Conditioned Implicit Representation for Image-based Human Reconstructioncited by 231
  16. 2019Texture Fields: Learning Texture Representations in Function Spacecited by 210
  17. 2017Unite the People: Closing the Loop Between 3D and 2D Human Representationscited by 205
  18. 2017Single-Shot Multi-Person 3D Pose Estimation From Monocular RGBcited by 195
  19. 2021SCANimate: Weakly Supervised Learning of Skinned Clothed Avatar Networkscited by 181
  20. 2019CvxNet: Learnable Convex Decompositioncited by 174
  21. 2016Learning a Predictable and Generative Vector Representation for Objectscited by 173
  22. 2020Beyond Static Features for Temporally Consistent 3D Human Pose and Shape from a Videocited by 163
  23. 2020DeepCap: Monocular Human Performance Capture Using Weak Supervisioncited by 162
  24. 2019NASA: Neural Articulated Shape Approximationcited by 149
  25. 2020Combining Implicit Function Learning and Parametric Models for 3D Human Reconstructioncited by 133
  26. 2020Points2Surf: Learning Implicit Surfaces from Point Cloud Patchescited by 122
  27. 2022Structured Local Radiance Fields for Human Avatar Modelingcited by 116
  28. 2019Pixel2Mesh++: Multi-View 3D Mesh Generation via Deformationcited by 103
  29. 2021Neural-GIF: Neural Generalized Implicit Functions for Animating People in Clothingcited by 102
  30. 2018DoubleFusion: Real-time Capture of Human Performances with Inner Body Shapes from a Single Depth Sensorcited by 95
  31. 2021NPMs: Neural Parametric Models for 3D Deformable Shapescited by 90
  32. 2022gDNA: Towards Generative Detailed Neural Avatarscited by 72
  33. 2020Neural Deformation Graphs for Globally-consistent Non-rigid Reconstructioncited by 67
  34. 2020CaSPR: Learning Canonical Spatiotemporal Point Cloud Representationscited by 51
  35. 2017O-CNN: Octree-based Convolutional Neural Networks for 3D Shape Analysiscited by 47
  36. 2021Locally Aware Piecewise Transformation Fields for 3D Human Mesh Registrationcited by 41
  37. 2015Dense Human Body Correspondences Using Convolutional Networkscited by 26
  38. 2021Learning Compositional Representation for 4D Captures with Neural ODEcited by 22

50 most cited of 54 All 54 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 1; 2023: 3; 2024: 3; 2025: 0; 2026: 1.

8 papers.

  1. 2023CloSET: Modeling Clothed Humans on Continuous Surface with Explicit Template Decompositioncited by 21
  2. 20234D Myocardium Reconstruction with Decoupled Motion and Shape Modelcited by 15
  3. 2023FourierHandFlow: Neural 4D Hand Representation Using Fourier Query Flowcited by 10
  4. 2024DynoSurf: Neural Deformation-based Temporally Consistent Dynamic Surface Reconstructioncited by 8
  5. 2024A Riemannian Approach for Spatiotemporal Analysis and Generation of 4D Tree-shaped Structurescited by 4
  6. 2022Deep representation learning: Fundamentals, Perspectives, Applications, and Open Challengescited by 3
  7. 2024ImplicitTerrain: a Continuous Surface Model for Terrain Data Analysiscited by 3
  8. 2026LayerGS: Decomposition and Inpainting of Layered 3D Human Avatars via 2D Gaussian Splattingcited by 1