mlsanityData to 7 Oct 2026

GFPose: Learning 3D Human Pose Prior with Gradient Fields

arXiv 2212.08641 ↗First posted 16 Dec 2022cs.CVcited by 57

Not on the map. Why?

Abstract (arXiv)

Learning 3D human pose prior is essential to human-centered AI. Here, we present GFPose, a versatile framework to model plausible 3D human poses for various applications. At the core of GFPose is a time-dependent score network, which estimates the gradient on each body joint and progressively denoises the perturbed 3D human pose to match a given task specification. During the denoising process, GFPose implicitly incorporates pose priors in gradients and unifies various discriminative and generative tasks in an elegant framework. Despite the simplicity, GFPose demonstrates great potential in several downstream tasks. Our experiments empirically show that 1) as a multi-hypothesis pose estimator, GFPose outperforms existing SOTAs by 20% on Human3.6M dataset. 2) as a single-hypothesis pose estimator, GFPose achieves comparable results to deterministic SOTAs, even with a vanilla backbone. 3) GFPose is able to produce diverse and realistic samples in pose denoising, completion and generation tasks. Project page https://sites.google.com/view/gfpose/

Key facts. Cited by 57 papers in the map (data through 7 Oct 2026). Builds on 51 of its 78 references that are in the map. First posted on arXiv 16 Dec 2022.

Builds on

51 of 78 references.

References · 51

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  3. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
  4. 2016Gaussian Error Linear Units (GELUs)cited by 3,431
  5. 2019Expressive Body Capture: 3D Hands, Face, and Body from a Single Imagecited by 1,600
  6. 2018Group Normalizationcited by 1,514
  7. 2020Improved Techniques for Training Score-Based Generative Modelscited by 1,036
  8. 2022Planning with Diffusion for Flexible Behavior Synthesiscited by 1,023
  9. 2016Stacked Hourglass Networks for Human Pose Estimationcited by 913
  10. 2017End-to-end Recovery of Human Shape and Posecited by 883
  11. 2016Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Imagecited by 692
  12. 2021Maximum Likelihood Training of Score-Based Diffusion Modelscited by 670
38 more
  1. 2019VIBE: Video Inference for Human Body Pose and Shape Estimationcited by 615
  2. 2021Solving Inverse Problems in Medical Imaging with Score-Based Generative Modelscited by 514
  3. 2021Action-Conditioned 3D Human Motion Synthesis with Transformer VAEcited by 497
  4. 2016Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervisioncited by 493
  5. 2017A simple yet effective baseline for 3d human pose estimationcited by 401
  6. 20183D human pose estimation in video with temporal convolutions and semi-supervised trainingcited by 401
  7. 2019Sliced Score Matching: A Scalable Approach to Density and Score Estimationcited by 381
  8. 2017Cascaded Pyramid Network for Multi-Person Pose Estimationcited by 341
  9. 2021HuMoR: 3D Human Motion Model for Robust Pose Estimationcited by 319
  10. 20213D Human Pose Estimation with Spatial and Temporal Transformerscited by 271
  11. 2021Revisiting Skeleton-based Action Recognitioncited by 256
  12. 2020Learning Gradient Fields for Shape Generationcited by 245
  13. 2022CLIFF: Carrying Location Information in Full Frames into Human Pose and Shape Estimationcited by 237
  14. 2019Semantic Graph Convolutional Networks for 3D Human Pose Regressioncited by 204
  15. 2021Character Controllers Using Motion VAEscited by 182
  16. 2021Learning Gradient Fields for Molecular Conformation Generationcited by 162
  17. 2021Probabilistic Modeling for Human Mesh Recoverycited by 152
  18. 2021MHFormer: Multi-Hypothesis Transformer for 3D Human Pose Estimationcited by 151
  19. 2017VNect: Real-time 3D Human Pose Estimation with a Single RGB Cameracited by 129
  20. 2022AvatarPoser: Articulated Full-Body Pose Tracking from Sparse Motion Sensingcited by 107
  21. 2021Energy-Based Learning for Scene Graph Generationcited by 104
  22. 2020SRNet: Improving Generalization in 3D Human Pose Estimation with a Split-and-Recombine Approachcited by 94
  23. 2021Graph Stacked Hourglass Networks for 3D Human Pose Estimationcited by 94
  24. 2019Generating Multiple Hypotheses for 3D Human Pose Estimation with Mixture Density Networkcited by 92
  25. 2022Pose-NDF: Modeling Human Pose Manifolds with Neural Distance Fieldscited by 85
  26. 2021Probabilistic Monocular 3D Human Pose Estimation with Normalizing Flowscited by 84
  27. 2021Score-Based Point Cloud Denoisingcited by 83
  28. 2019Monocular 3D Human Pose Estimation by Generation and Ordinal Rankingcited by 76
  29. 2022QuestSim: Human Motion Tracking from Sparse Sensors with Simulated Avatarscited by 74
  30. 2021Learning Skeletal Graph Neural Networks for Hard 3D Pose Estimationcited by 62
  31. 2022DiffuStereo: High Quality Human Reconstruction via Diffusion-based Stereo Using Sparse Camerascited by 43
  32. 2021Adversarial Parametric Pose Priorcited by 38
  33. 2021Context Modeling in 3D Human Pose Estimation: A Unified Perspectivecited by 37
  34. 2020Motion Capture from Internet Videoscited by 33
  35. 2017Generating Multiple Diverse Hypotheses for Human 3D Pose Consistent with 2D Joint Detectionscited by 30
  36. 2020Fusing Wearable IMUs with Multi-View Images for Human Pose Estimation: A Geometric Approachcited by 27
  37. 2020GraphMDN: Leveraging graph structure and deep learning to solve inverse problemscited by 26
  38. 2020Weakly Supervised Generative Network for Multiple 3D Human Pose Hypothesescited by 25

50 most cited of 51 All 51 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 14; 2024: 23; 2025: 11; 2026: 9.

57 papers.

Sort:

By area:

  1. 2024RingID: Rethinking Tree-Ring Watermarking for Enhanced Multi-Key Identificationcited by 87
  2. 2024Estimating Body and Hand Motion in an Ego-sensed Worldcited by 56
  3. 2024Omni6DPose: A Benchmark and Model for Universal 6D Object Pose Estimation and Trackingcited by 48
  4. 2023GenPose: Generative Category-level Object Pose Estimation via Diffusion Modelscited by 47
  5. 20233D Human Mesh Estimation from Virtual Markerscited by 44
  6. 2023Egocentric Whole-Body Motion Capture with FisheyeViT and Diffusion-Based Motion Refinementcited by 31
  7. 2024WMAdapter: Adding WaterMark Control to Latent Diffusion Modelscited by 29
  8. 2024NRDF: Neural Riemannian Distance Fields for Learning Articulated Pose Priorscited by 27
  9. 2024HMD^2: Environment-aware Motion Generation from Single Egocentric Head-Mounted Devicecited by 26
  10. 2023Back to Optimization: Diffusion-based Zero-Shot 3D Human Pose Estimationcited by 24
  11. 2023GraspGF: Learning Score-based Grasping Primitive for Human-assisting Dexterous Graspingcited by 23
  12. 2024RELI11D: A Comprehensive Multimodal Human Motion Dataset and Methodcited by 16
38 more
  1. 2024MacDiff: Unified Skeleton Modeling with Masked Conditional Diffusioncited by 15
  2. 2024HHMR: Holistic Hand Mesh Recovery by Enhancing the Multimodal Controllability of Graph Diffusion Modelscited by 14
  3. 2025AthletePose3D: A Benchmark Dataset for 3D Human Pose Estimation and Kinematic Validation in Athletic Movementscited by 14
  4. 2023Proactive Multi-Camera Collaboration For 3D Human Pose Estimationcited by 13
  5. 2024Disentangled Diffusion-Based 3D Human Pose Estimation with Hierarchical Spatial and Temporal Denoisercited by 13
  6. 2025DPoser-X: Diffusion Model as Robust 3D Whole-body Human Pose Priorcited by 13
  7. 2023Score-PA: Score-based 3D Part Assemblycited by 11
  8. 2024Steganalysis on Digital Watermarking: Is Your Defense Truly Impervious?cited by 10
  9. 2023Unsupervised 3D Pose Estimation with Non-Rigid Structure-from-Motion Modelingcited by 7
  10. 2024Normalizing Flows on the Product Space of SO(3) Manifolds for Probabilistic Human Pose Modelingcited by 7
  11. 2023ManiPose: Manifold-Constrained Multi-Hypothesis 3D Human Pose Estimationcited by 6
  12. 2025Geometric Neural Distance Fields for Learning Human Motion Priorscited by 6
  13. 2024Diversifying Human Pose in Synthetic Data for Aerial-view Human Detectioncited by 5
  14. 2025Learning 3D Object Spatial Relationships from Pre-trained 2D Diffusion Modelscited by 5
  15. 2023MPM: A Unified 2D-3D Human Pose Representation via Masked Pose Modelingcited by 4
  16. 2023Learning Gradient Fields for Scalable and Generalizable Irregular Packingcited by 3
  17. 2024PADS: Plug-and-Play 3D Human Pose Analysis via Diffusion Generative Modelingcited by 3
  18. 2024Dexterous Functional Pre-Grasp Manipulation with Diffusion Policycited by 3
  19. 2024Occlusion Handling in 3D Human Pose Estimation with Perturbed Positional Encodingcited by 3
  20. 2024ViMo: Generating Motions from Casual Videoscited by 3
  21. 2025ClimbingCap: Multi-Modal Dataset and Method for Rock Climbing in World Coordinatecited by 3
  22. 2026Towards Motion Turing Test: Evaluating Human-Likeness in Humanoid Robotscited by 3
  23. 2023UniHPE: Towards Unified Human Pose Estimation via Contrastive Learningcited by 2
  24. 2023STRIDE: Single-video based Temporally Continuous Occlusion-Robust 3D Pose Estimationcited by 2
  25. 2024Platypose: Calibrated Zero-Shot Multi-Hypothesis 3D Human Motion Estimationcited by 2
  26. 2024SocialGFs: Learning Social Gradient Fields for Multi-Agent Reinforcement Learningcited by 2
  27. 2024Multi-modal Pose Diffuser: A Multimodal Generative Conditional Pose Priorcited by 2
  28. 2026Flow Matching for Probabilistic Monocular 3D Human Pose Estimationcited by 2
  29. 2026UniHand: A Unified Model for Diverse Controlled 4D Hand Motion Modelingcited by 2
  30. 2026MuPPet: Multi-person 2D-to-3D Pose Liftingcited by 2
  31. 2024Diffusion-based Pose Refinement and Muti-hypothesis Generation for 3D Human Pose Estimaitoncited by 1
  32. 2025FastDDHPose: Towards Unified, Efficient, and Disentangled 3D Human Pose Estimationcited by 1
  33. 2026FlashCap: Millisecond-Accurate Human Motion Capture via Flashing LEDs and Event-Based Visioncited by 1
  34. 2023QPoser: Quantized Explicit Pose Prior Modeling for Controllable Pose Generationcited by 0
  35. 2024Learning Human Motion from Monocular Videos via Cross-Modal Manifold Alignmentcited by 0
  36. 2024Probablistic Restoration with Adaptive Noise Sampling for 3D Human Pose Estimationcited by 0
  37. 2025HDiffTG: A Lightweight Hybrid Diffusion-Transformer-GCN Architecture for 3D Human Pose Estimationcited by 0
  38. 2025Neural Human Pose Priorcited by 0

50 most cited of 57 All 57 (JSON)