mlsanityData to 7 Oct 2026

NDF: Neural Deformable Fields for Dynamic Human Modelling

arXiv 2207.09193 ↗First posted 19 Jul 2022cs.CV cs.AIcited by 14

Not on the map. Why?

Abstract (arXiv)

We propose Neural Deformable Fields (NDF), a new representation for dynamic human digitization from a multi-view video. Recent works proposed to represent a dynamic human body with shared canonical neural radiance fields which links to the observation space with deformation fields estimations. However, the learned canonical representation is static and the current design of the deformation fields is not able to represent large movements or detailed geometry changes. In this paper, we propose to learn a neural deformable field wrapped around a fitted parametric body model to represent the dynamic human. The NDF is spatially aligned by the underlying reference surface. A neural network is then learned to map pose to the dynamics of NDF. The proposed NDF representation can synthesize the digitized performer with novel views and novel poses with a detailed and reasonable dynamic appearance. Experiments show that our method significantly outperforms recent human synthesis methods.

Key facts. Cited by 14 papers in the map (data through 7 Oct 2026). Builds on 21 of its 32 references that are in the map. First posted on arXiv 19 Jul 2022.

Builds on

21 of 32 references.

References · 21

  1. 2020pixelNeRF: Neural Radiance Fields from One or Few Imagescited by 1,574
  2. 2020D-NeRF: Neural Radiance Fields for Dynamic Scenescited by 1,459
  3. 2020NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collectionscited by 1,230
  4. 2020Nerfies: Deformable Neural Radiance Fieldscited by 1,194
  5. 2020Neural Sparse Voxel Fieldscited by 959
  6. 2019Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representationscited by 864
  7. 2020Neural Scene Flow Fields for Space-Time View Synthesis of Dynamic Scenescited by 750
  8. 2020Neural Body: Implicit Neural Representations with Structured Latent Codes for Novel View Synthesis of Dynamic Humanscited by 634
  9. 2021FastNeRF: High-Fidelity Neural Rendering at 200FPScited by 510
  10. 2018DeepVoxels: Learning Persistent 3D Feature Embeddingscited by 401
  11. 2021Animatable Neural Radiance Fields for Modeling Dynamic Human Bodiescited by 361
  12. 2019Neural Point-Based Graphicscited by 326
9 more
  1. 2018Total Capture: A 3D Deformation Model for Tracking Faces, Hands, and Bodiescited by 239
  2. 2021HyperNeRF: A Higher-Dimensional Representation for Topologically Varying Neural Radiance Fieldscited by 210
  3. 2018Stereo Magnification: Learning View Synthesis using Multiplane Imagescited by 206
  4. 2021Neural Articulated Radiance Fieldcited by 196
  5. 2021Real-time Deep Dynamic Characterscited by 133
  6. 2021Neural Actor: Neural Free-view Synthesis of Human Actors with Pose Controlcited by 106
  7. 2019Neural Point Cloud Rendering via Multi-Plane Projectioncited by 60
  8. 2021DoubleField: Bridging the Neural Surface and Radiance Fields for High-fidelity Human Reconstruction and Renderingcited by 52
  9. 2020Neural Human Video Rendering by Learning Dynamic Textures and Rendering-to-Video Translationcited by 13

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 7; 2024: 4; 2025: 2.

14 papers.

Sort:

  1. 2023Learning Neural Volumetric Representations of Dynamic Humans in Minutescited by 70
  2. 2024GoMAvatar: Efficient Animatable Human Modeling from Monocular Video Using Gaussians-on-Meshcited by 51
  3. 2024Grid4D: 4D Decomposed Hash Encoding for High-Fidelity Dynamic Gaussian Splattingcited by 49
  4. 2023textttNePhi: Neural Deformation Fields for Approximately Diffeomorphic Medical Image Registrationcited by 8
  5. 2025DASH: 4D Hash Encoding with Self-Supervised Decomposition for Real-Time Dynamic Scene Renderingcited by 8
  6. 2023IntrinsicNGP: Intrinsic Coordinate based Hash Encoding for Human NeRFcited by 7
  7. 2023NAISR: A 3D Neural Additive Model for Interpretable Shape Representationcited by 7
  8. 2023Explicifying Neural Implicit Fields for Efficient Dynamic Human Avatar Modeling via a Neural Explicit Surfacecited by 6
  9. 2024Motion-Oriented Compositional Neural Radiance Fields for Monocular Dynamic Human Modelingcited by 4
  10. 2024NECA: Neural Customizable Human Avatarcited by 3
  11. 2023Efficient Meshy Neural Fields for Animatable Human Avatarscited by 2
  12. 2022Pathway to Future Symbiotic Creativitycited by 0
2 more
  1. 2023UVA: Towards Unified Volumetric Avatar for View Synthesis, Pose rendering, Geometry and Texture Editingcited by 0
  2. 2025Fast and Physically-based Neural Explicit Surface for Relightable Human Avatarscited by 0