mlsanityData to 14 Oct 2026

Geometric Neural Distance Fields for Learning Human Motion Priors

arXiv 2509.09667 ↗First posted 11 Sep 2025cs.CVcited by 6

Not on the map. Why?

Abstract (arXiv)

We introduce Neural Riemannian Motion Fields (NRMF), a novel 3D generative human motion prior that enables robust, temporally consistent, and physically plausible 3D motion recovery. Unlike existing VAE or diffusion-based methods, our higher-order motion prior explicitly models the human motion in the zero level set of a collection of neural distance fields (NDFs) corresponding to pose, transition (velocity), and acceleration dynamics. Our framework is rigorous in the sense that our NDFs are constructed on the product space of joint rotations, their angular velocities, and angular accelerations, respecting the geometry of the underlying articulations. We further introduce: (i) a novel adaptive-step hybrid algorithm for projecting onto the set of plausible motions, and (ii) a novel geometric integrator to "roll out" realistic motion trajectories during test-time-optimization and generation. Our experiments show significant and consistent gains: trained on the AMASS dataset, NRMF remarkably generalizes across multiple input modalities and to diverse tasks ranging from denoising to motion in-betweening and fitting to partial 2D / 3D observations.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 44 of its 61 references that are in the map. First posted on arXiv 11 Sep 2025.

Builds on

44 of 61 references.

References · 44

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  2. 2017Billion-scale similarity search with GPUscited by 2,497
  3. 2017Rethinking Atrous Convolution for Semantic Image Segmentationcited by 2,161
  4. 2019Expressive Body Capture: 3D Hands, Face, and Body from a Single Imagecited by 1,612
  5. 2019AMASS: Archive of Motion Capture as Surface Shapescited by 1,236
  6. 2018OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,162
  7. 2022Human Motion Diffusion Modelcited by 1,080
  8. 2016Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Imagecited by 695
  9. 2019VIBE: Video Inference for Human Body Pose and Shape Estimationcited by 620
  10. 2023Human Motion Diffusion as a Generative Priorcited by 357
  11. 2023Humans in 4D: Reconstructing and Tracking Humans with Transformerscited by 350
  12. 2021PARE: Part Attention Regressor for 3D Human Body Estimationcited by 337
32 more
  1. 2021HuMoR: 3D Human Motion Model for Robust Pose Estimationcited by 324
  2. 2019Resolving 3D Human Pose Ambiguities with 3D Scene Constraintscited by 295
  3. 2020Neural Unsigned Distance Fields for Implicit Function Learningcited by 265
  4. 2022CLIFF: Carrying Location Information in Full Frames into Human Pose and Shape Estimationcited by 238
  5. 2023TMR: Text-to-Motion Retrieval Using Contrastive 3D Human Motion Synthesiscited by 198
  6. 2021Character Controllers Using Motion VAEscited by 184
  7. 2023SMPLer-X: Scaling Up Expressive Human Pose and Shape Estimationcited by 155
  8. 2022PyMAF-X: Towards Well-aligned Full-body Model Regression from Monocular Imagescited by 153
  9. 2021EgoBody: Human Body Shape and Motion of Interacting People from Head-Mounted Devicescited by 139
  10. 2021Collaborative Regression of Expressive Bodies using Moderationcited by 137
  11. 2018PlaneRCNN: 3D Plane Detection and Reconstruction from a Single Imagecited by 105
  12. 2016Pymanopt: A Python Toolbox for Optimization on Manifolds using Automatic Differentiationcited by 94
  13. 2023TRACE: 5D Temporal Regression of Avatars with Dynamic Cameras in 3D Environmentscited by 91
  14. 2022Pose-NDF: Modeling Human Pose Manifolds with Neural Distance Fieldscited by 85
  15. 2023NIFTY: Neural Object Interaction Fields for Guided Human Motion Synthesiscited by 78
  16. 2022NeMF: Neural Motion Fields for Kinematic Animationcited by 68
  17. 2022GFPose: Learning 3D Human Pose Prior with Gradient Fieldscited by 57
  18. 2023Make-An-Animation: Large-Scale Text-conditional 3D Human Motion Generationcited by 56
  19. 2024Dyn-HaMR: Recovering 4D Interacting Hand Motion from a Dynamic Cameracited by 51
  20. 2024StableMoFusion: Towards Robust and Efficient Diffusion-based Motion Generation Frameworkcited by 50
  21. 2024RoHM: Robust Human Motion Reconstruction via Diffusioncited by 48
  22. 2021Adversarial Parametric Pose Priorcited by 38
  23. 2020MeTRAbs: Metric-Scale Truncation-Robust Heatmaps for Absolute 3D Human Pose Estimationcited by 35
  24. 2021Projective Manifold Gradient Layer for Deep Rotation Regressioncited by 31
  25. 2024NRDF: Neural Riemannian Distance Fields for Learning Articulated Pose Priorscited by 27
  26. 2019Probabilistic Permutation Synchronization using the Riemannian Structure of the Birkhoff Polytopecited by 26
  27. 2018Bayesian Pose Graph Optimization via Bingham Distributions and Tempered Geodesic MCMCcited by 19
  28. 2023DPoser: Diffusion Model as Robust 3D Human Pose Priorcited by 17
  29. 2022PoseBERT: A Generic Transformer Module for Temporal 3D Human Modelingcited by 15
  30. 2024SMPLer: Taming Transformers for Monocular 3D Human Shape and Pose Estimationcited by 9
  31. 2025Forecasting Continuous Non-Conservative Dynamical Systems in SO(3)cited by 3
  32. 2024MoManifold: Learning to Measure 3D Human Motion via Decoupled Joint Acceleration Manifoldscited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 5.

6 papers.

  1. 2025MoLingo: Motion-Language Alignment for Text-to-Human Motion Generationcited by 2
  2. 2026Parallelised Differentiable Straightest Geodesics for 3D Meshescited by 2
  3. 2026PDF-HR: Pose Distance Fields for Humanoid Robotscited by 1
  4. 2026SAMoR: Motion Modelling for Articulated Objects of Any Skeleton and Topologycited by 1
  5. 2026Spatial Temporal Synergy: Balancing Change and Invariance in Text Driven 3D Human Motion Editingcited by 1
  6. 2026PFM-HR: Pose Flow Matching for Humanoid Robotscited by 0