mlsanityData to 7 Oct 2026

HuMoR: 3D Human Motion Model for Robust Pose Estimation

arXiv 2105.04668 ↗First posted 10 May 2021cs.CV cs.LGcited by 319

Not on the map. Why?

Cited by 25 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We introduce HuMoR: a 3D Human Motion Model for Robust Estimation of temporal pose and shape. Though substantial progress has been made in estimating 3D human motion and shape from dynamic observations, recovering plausible pose sequences in the presence of noise and occlusions remains a challenge. For this purpose, we propose an expressive generative model in the form of a conditional variational autoencoder, which learns a distribution of the change in pose at each step of a motion sequence. Furthermore, we introduce a flexible optimization-based approach that leverages HuMoR as a motion prior to robustly estimate plausible pose and shape from ambiguous observations. Through extensive evaluations, we demonstrate that our model generalizes to diverse motions and body shapes after training on a large motion capture dataset, and enables motion reconstruction from multiple input modalities including 3D keypoints and RGB(-D) videos.

Key facts. Cited by 319 papers in the map (data through 7 Oct 2026). Builds on 56 of its 108 references that are in the map. First posted on arXiv 10 May 2021.

Builds on

56 of 108 references.

References · 56

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2013Auto-Encoding Variational Bayescited by 3,980
  3. 2018Neural Ordinary Differential Equationscited by 3,733
  4. 2017Rethinking Atrous Convolution for Semantic Image Segmentationcited by 2,154
  5. 2014Conditional Generative Adversarial Netscited by 2,152
  6. 2019Expressive Body Capture: 3D Hands, Face, and Body from a Single Imagecited by 1,600
  7. 2018Group Normalizationcited by 1,514
  8. 2019AMASS: Archive of Motion Capture as Surface Shapescited by 1,208
  9. 2018OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,161
  10. 2017End-to-end Recovery of Human Shape and Posecited by 883
  11. 2019PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitizationcited by 818
  12. 2015Scheduled Sampling for Sequence Prediction with Recurrent Neural Networkscited by 779
38 more
  1. 2016Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Imagecited by 692
  2. 2019Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loopcited by 625
  3. 2019VIBE: Video Inference for Human Body Pose and Shape Estimationcited by 615
  4. 2015Generating Sentences from a Continuous Spacecited by 607
  5. 2018DensePose: Dense Human Pose Estimation In The Wildcited by 573
  6. 20183D human pose estimation in video with temporal convolutions and semi-supervised trainingcited by 401
  7. 2017Learning from Synthetic Humanscited by 358
  8. 2021PARE: Part Attention Regressor for 3D Human Body Estimationcited by 334
  9. 2018Learning 3D Human Dynamics from Videocited by 315
  10. 2019Resolving 3D Human Pose Ambiguities with 3D Scene Constraintscited by 294
  11. 2018Learning to Estimate 3D Human Pose and Shape from a Single Color Imagecited by 226
  12. 2017Unite the People: Closing the Loop Between 3D and 2D Human Representationscited by 205
  13. 2020DLow: Diversifying Latent Flows for Diverse Human Motion Predictioncited by 184
  14. 2021Character Controllers Using Motion VAEscited by 182
  15. 2020Populating 3D Scenes by Learning Human-Scene Interactioncited by 164
  16. 2018Monocular Total Capture: Posing Face, Body, and Hands in the Wildcited by 162
  17. 2020DeepCap: Monocular Human Performance Capture Using Weak Supervisioncited by 162
  18. 2020Monocular Expressive Body Regression through Body-Driven Attentioncited by 155
  19. 2018BodyNet: Volumetric Inference of 3D Human Body Shapescited by 141
  20. 2019Don't Blame the ELBO! A Linear VAE Perspective on Posterior Collapsecited by 120
  21. 2020We are More than Our Joints: Predicting how 3D Bodies Movecited by 115
  22. 2021SimPoE: Simulated Character Control for 3D Human Pose Estimationcited by 111
  23. 2019Exploiting temporal context for 3D human pose estimation in the wildcited by 110
  24. 2018PlaneRCNN: 3D Plane Detection and Reconstruction from a Single Imagecited by 105
  25. 20203D Human Motion Estimation via Motion Compression and Refinementcited by 98
  26. 2019Structured Prediction Helps 3D Human Motion Modellingcited by 96
  27. 2020Weakly Supervised 3D Human Pose and Shape Reconstruction with Normalizing Flowscited by 94
  28. 2020Contact and Human Dynamics from Monocular Videocited by 94
  29. 2017Towards Accurate Markerless Human Shape and Pose Estimation over Timecited by 92
  30. 2019Human Mesh Recovery from Monocular Images via a Skeleton-disentangled Representationcited by 87
  31. 2019Context-aware Human Motion Predictioncited by 83
  32. 2019Sim2real transfer learning for 3D human pose estimation: motion to the rescuecited by 75
  33. 2019Holistic++ Scene Understanding: Single-view 3D Holistic Scene Parsing and Human Pose Estimation with Human-Object Interaction and Physical Commonsensecited by 71
  34. 2020Hierarchical Kinematic Human Mesh Recoverycited by 71
  35. 2019XNect: Real-time Multi-Person 3D Motion Capture with a Single RGB Cameracited by 68
  36. 2019Predicting 3D Human Dynamics from Videocited by 51
  37. 20203D Multi-bodies: Fitting Sets of Plausible 3D Human Models to Ambiguous Image Datacited by 50
  38. 2019Estimating 3D Motion and Forces of Person-Object Interactions from Monocular Videocited by 48

50 most cited of 56 All 56 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 10; 2022: 50; 2023: 81; 2024: 75; 2025: 57; 2026: 46.

319 papers.

Sort:

By area:

  1. 2022Executing your Commands via Motion Diffusion in Latent Spacecited by 567
  2. 2023Humans in 4D: Reconstructing and Tracking Humans with Transformerscited by 344
  3. 2022EDGE: Editable Dance Generation From Musiccited by 284
  4. 2023PointOdyssey: A Large-Scale Synthetic Dataset for Long-Term Point Trackingcited by 274
  5. 2023Diffusion-based Generation, Optimization, and Planning in 3D Scenescited by 237
  6. 2023OmniControl: Control Any Joint at Any Time for Human Motion Generationcited by 233
  7. 2023Guided Motion Diffusion for Controllable Human Motion Synthesiscited by 221
  8. 2022MoFusion: A Framework for Denoising-Diffusion-based Motion Synthesiscited by 218
  9. 2023InterGen: Diffusion-based Multi-human Motion Generation under Complex Interactionscited by 205
  10. 2023WHAM: Reconstructing World-grounded Humans with Accurate 3D Motioncited by 200
  11. 2022Capturing and Inferring Dense Full-Body Human-Scene Contactcited by 176
  12. 2022NeRF: Neural Radiance Field in 3D Vision: A Comprehensive Review (Updated Post-Gaussian Splatting)cited by 156
38 more
  1. 2022PyMAF-X: Towards Well-aligned Full-body Model Regression from Monocular Imagescited by 152
  2. 2021GLAMR: Global Occlusion-Aware Human Mesh Recovery with Dynamic Camerascited by 151
  3. 2021GOAL: Generating 4D Whole-Body Motion for Hand-Object Graspingcited by 142
  4. 2021Putting People in their Place: Monocular Regression of 3D People in Depthcited by 141
  5. 2023Decoupling Human and Camera Motion from Videos in the Wildcited by 140
  6. 2023Trace and Pace: Controllable Pedestrian Animation via Guided Trajectory Diffusioncited by 137
  7. 2021Generating Useful Accident-Prone Driving Scenarios via a Learned Traffic Priorcited by 136
  8. 2024World-Grounded Human Motion Recovery via Gravity-View Coordinatescited by 127
  9. 2023State of the Art on Diffusion Models for Visual Computingcited by 126
  10. 2022IMos: Intent-Driven Full-Body Motion Synthesis for Human-Object Interactionscited by 121
  11. 2023Universal Humanoid Motion Representations for Physics-Based Controlcited by 109
  12. 2024Nymeria: A Massive Collection of Multimodal Egocentric Daily Motion in the Wildcited by 109
  13. 2024TRAM: Global Trajectory and Motion of 3D Humans from in-the-wild Videoscited by 105
  14. 2023Avatars Grow Legs: Generating Smooth Human Motion from Sparse Tracking Inputs with Diffusion Modelcited by 104
  15. 2022Recovering 3D Human Mesh from Monocular Images: A Surveycited by 103
  16. 20233D Human Pose Estimation via Intuitive Physicscited by 100
  17. 2023Optimizing Diffusion Noise Can Serve As Universal Motion Priorscited by 97
  18. 2023Human Motion Generation: A Surveycited by 95
  19. 2022Ego-Body Pose Estimation via Ego-Head Pose Estimationcited by 93
  20. 2023TLControl: Trajectory and Language Control for Human Motion Synthesiscited by 93
  21. 2022InterCap: Joint Markerless 3D Tracking of Humans and Objects in Interactioncited by 90
  22. 2021SAGA: Stochastic Whole-Body Grasping with Contactcited by 89
  23. 2023EMDM: Efficient Motion Diffusion Model for Fast and High-Quality Motion Generationcited by 88
  24. 2024Multi-Track Timeline Control for Text-Driven 3D Human Motion Generationcited by 88
  25. 2022Pose-NDF: Modeling Human Pose Manifolds with Neural Distance Fieldscited by 85
  26. 2023Paint-it: Text-to-Texture Synthesis via Deep Convolutional Texture Map Optimization and Physically-Based Renderingcited by 84
  27. 2022GIMO: Gaze-Informed Human Motion Prediction in Contextcited by 81
  28. 2024DartControl: A Diffusion-Based Autoregressive Motion Model for Real-Time Text-Driven Motion Controlcited by 80
  29. 2023CIRCLE: Capture In Rich Contextual Environmentscited by 79
  30. 2022PoseGPT: Quantization-based 3D Human Motion Generation and Forecastingcited by 78
  31. 2023NIFTY: Neural Object Interaction Fields for Guided Human Motion Synthesiscited by 78
  32. 2022Transformer Inertial Poser: Real-time Human Motion Reconstruction from Sparse IMUs with Simultaneous Terrain Generationcited by 75
  33. 2022QuestSim: Human Motion Tracking from Sparse Sensors with Simulated Avatarscited by 74
  34. 2021Intrinsic Dimension, Persistent Homology and Generalization in Neural Networkscited by 70
  35. 2025PromptHMR: Promptable Human Mesh Recoverycited by 70
  36. 2022NeMF: Neural Motion Fields for Kinematic Animationcited by 66
  37. 2021SmoothNet: A Plug-and-Play Network for Refining Human Poses in Videoscited by 64
  38. 2021The Wanderings of Odysseus in 3D Scenescited by 59

50 most cited of 319 All 319 (JSON)