mlsanityData to 7 Oct 2026

3D Human Motion Estimation via Motion Compression and Refinement

arXiv 2008.03789 ↗First posted 9 Aug 2020cs.CVcited by 98

Not on the map. Why?

Abstract (arXiv)

We develop a technique for generating smooth and accurate 3D human pose and motion estimates from RGB video sequences. Our method, which we call Motion Estimation via Variational Autoencoder (MEVA), decomposes a temporal sequence of human motion into a smooth motion representation using auto-encoder-based motion compression and a residual representation learned through motion refinement. This two-step encoding of human motion captures human motion in two stages: a general human motion estimation step that captures the coarse overall motion, and a residual estimation that adds back person-specific motion details. Experiments show that our method produces both smooth and accurate 3D human pose and motion estimates.

Key facts. Cited by 98 papers in the map (data through 7 Oct 2026). First posted on arXiv 9 Aug 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 23; 2022: 20; 2023: 22; 2024: 17; 2025: 8; 2026: 8.

98 papers.

Sort:

By area:

  1. 2021Action-Conditioned 3D Human Motion Synthesis with Transformer VAEcited by 497
  2. 2023Humans in 4D: Reconstructing and Tracking Humans with Transformerscited by 344
  3. 2021PARE: Part Attention Regressor for 3D Human Body Estimationcited by 334
  4. 2021HuMoR: 3D Human Motion Model for Robust Pose Estimationcited by 319
  5. 2023WHAM: Reconstructing World-grounded Humans with Accurate 3D Motioncited by 200
  6. 2022MotionBERT: A Unified Perspective on Learning Human Motion Representationscited by 188
  7. 2022PyMAF-X: Towards Well-aligned Full-body Model Regression from Monocular Imagescited by 152
  8. 2021GLAMR: Global Occlusion-Aware Human Mesh Recovery with Dynamic Camerascited by 151
  9. 2023Decoupling Human and Camera Motion from Videos in the Wildcited by 140
  10. 2021Human POSEitioning System (HPS): 3D Human Pose Estimation and Self-localization in Large Scenes from Body-Mounted Sensorscited by 137
  11. 2021EgoBody: Human Body Shape and Motion of Interacting People from Head-Mounted Devicescited by 136
  12. 2024World-Grounded Human Motion Recovery via Gravity-View Coordinatescited by 127
38 more
  1. 2022HuMMan: Multi-Modal 4D Human Dataset for Versatile Sensing and Modelingcited by 115
  2. 2021SimPoE: Simulated Character Control for 3D Human Pose Estimationcited by 111
  3. 2023Universal Humanoid Motion Representations for Physics-Based Controlcited by 109
  4. 2024TRAM: Global Trajectory and Motion of 3D Humans from in-the-wild Videoscited by 105
  5. 2022Recovering 3D Human Mesh from Monocular Images: A Surveycited by 103
  6. 2021Dynamics-Regulated Kinematic Policy for Egocentric Pose Estimationcited by 101
  7. 2021Learning Motion Priors for 4D Human Body Capture in 3D Scenescited by 98
  8. 2022Ego-Body Pose Estimation via Ego-Head Pose Estimationcited by 93
  9. 2022GIMO: Gaze-Informed Human Motion Prediction in Contextcited by 81
  10. 2021MobRecon: Mobile-Friendly Hand Mesh Reconstruction from Monocular Imagecited by 74
  11. 2025PromptHMR: Promptable Human Mesh Recoverycited by 70
  12. 2022TOCH: Spatio-Temporal Object-to-Hand Correspondence for Motion Refinementcited by 69
  13. 2021SmoothNet: A Plug-and-Play Network for Refining Human Poses in Videoscited by 64
  14. 2021Playing for 3D Human Recoverycited by 63
  15. 2021Encoder-decoder with Multi-level Attention for 3D Human Shape and Pose Estimationcited by 62
  16. 2022Capturing Humans in Motion: Temporal-Attentive 3D Human Pose and Shape Estimation from Monocular Videocited by 59
  17. 2021Estimating Egocentric 3D Human Pose in Global Spacecited by 56
  18. 2023Global-to-Local Modeling for Video-based 3D Human Pose and Shape Estimationcited by 46
  19. 2024RoHM: Robust Human Motion Reconstruction via Diffusioncited by 46
  20. 2023NIKI: Neural Inverse Kinematics with Invertible Neural Networks for 3D Human Pose and Shape Estimationcited by 45
  21. 2021D3D-HOI: Dynamic 3D Human-Object Interactions from Videoscited by 39
  22. 2022D&D: Learning Human Dynamics from Dynamic Cameracited by 39
  23. 2021Task-Generic Hierarchical Human Motion Prior using VAEscited by 33
  24. 2023PACE: Human and Camera Motion Estimation from in-the-wild Videoscited by 33
  25. 2023PSVT: End-to-End Multi-person 3D Pose and Shape Estimation with Progressive Video Transformerscited by 31
  26. 2022Embodied Scene-aware Human Pose Estimationcited by 28
  27. 2022Benchmarking and Analyzing 3D Human Pose and Shape Estimation Beyond Algorithmscited by 28
  28. 2024PhysPT: Physics-aware Pretrained Transformer for Estimating Human Dynamics from Monocular Videoscited by 27
  29. 2021Dynamic Multi-Person Mesh Recovery From Uncalibrated Multi-View Camerascited by 26
  30. 2023Co-Evolution of Pose and Mesh for 3D Human Body Estimation from Videocited by 25
  31. 2022FLAG3D: A 3D Fitness Activity Dataset with Language Instructioncited by 23
  32. 2023Cyclic Test-Time Adaptation on Monocular Video for 3D Human Mesh Reconstructioncited by 18
  33. 2024MultiPhys: Multi-Person Physics-aware 3D Motion Estimationcited by 18
  34. 2021Tracking People by Predicting 3D Appearance, Location & Posecited by 15
  35. 2022Occluded Human Body Capture with Self-Supervised Spatial-Temporal Motion Priorcited by 15
  36. 2022PoseBERT: A Generic Transformer Module for Temporal 3D Human Modelingcited by 15
  37. 2024COIN: Control-Inpainting Diffusion Prior for Human and Camera Motion Estimationcited by 15
  38. 2023VQ-HPS: Human Pose and Shape Estimation in a Vector-Quantized Latent Spacecited by 13

50 most cited of 98 All 98 (JSON)