mlsanityData to 7 Oct 2026

Contact and Human Dynamics from Monocular Video

arXiv 2007.11678 ↗First posted 22 Jul 2020cs.CVcited by 94

Not on the map. Why?

Abstract (arXiv)

Existing deep models predict 2D and 3D kinematic poses from video that are approximately accurate, but contain visible errors that violate physical constraints, such as feet penetrating the ground and bodies leaning at extreme angles. In this paper, we present a physics-based method for inferring 3D human motion from video sequences that takes initial 2D and 3D pose estimates as input. We first estimate ground contact timings with a novel prediction network which is trained without hand-labeled data. A physics-based trajectory optimization then solves for a physically-plausible motion, based on the inputs. We show this process produces motions that are significantly more realistic than those from purely kinematic methods, substantially improving quantitative measures of both kinematic and dynamic plausibility. We demonstrate our method on character animation and pose estimation tasks on dynamic motions of dancing and sports with complex contact patterns.

Key facts. Cited by 94 papers in the map (data through 7 Oct 2026). First posted on arXiv 22 Jul 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 16; 2022: 18; 2023: 16; 2024: 19; 2025: 16; 2026: 9.

94 papers.

Sort:

By area:

  1. 2022PhysDiff: Physics-Guided Human Motion Diffusion Modelcited by 365
  2. 2021HuMoR: 3D Human Motion Model for Robust Pose Estimationcited by 319
  3. 2022Capturing and Inferring Dense Full-Body Human-Scene Contactcited by 176
  4. 2023Decoupling Human and Camera Motion from Videos in the Wildcited by 140
  5. 2021ContactOpt: Optimizing Contact to Improve Graspscited by 137
  6. 2021SimPoE: Simulated Character Control for 3D Human Pose Estimationcited by 111
  7. 2021D-Grasp: Physically Plausible Dynamic Grasp Synthesis for Hand-Object Interactionscited by 109
  8. 2022Recovering 3D Human Mesh from Monocular Images: A Surveycited by 103
  9. 2021Dynamics-Regulated Kinematic Policy for Egocentric Pose Estimationcited by 101
  10. 20233D Human Pose Estimation via Intuitive Physicscited by 100
  11. 2021Learning Motion Priors for 4D Human Body Capture in 3D Scenescited by 98
  12. 2022CHORE: Contact, Human and Object REconstruction from a single RGB imagecited by 95
38 more
  1. 2021Neural Monocular 3D Human Motion Capture with Physical Awarenesscited by 70
  2. 2021Physics-based Human Motion Estimation and Synthesis from Videoscited by 65
  3. 2024Estimating Body and Hand Motion in an Ego-sensed Worldcited by 56
  4. 2022FLAG: Flow-based 3D Avatar Generation from Sparse Observationscited by 54
  5. 2023DECO: Dense Estimation of 3D Human-Scene Contact In The Wildcited by 54
  6. 2021TRiPOD: Human Trajectory and Pose Dynamics Forecasting in the Wildcited by 52
  7. 2023LEMON: Learning 3D Human-Object Interaction Relation from 2D Imagescited by 49
  8. 2024RoHM: Robust Human Motion Reconstruction via Diffusioncited by 46
  9. 2024PhyRecon: Physically Plausible Neural Scene Reconstructioncited by 44
  10. 2023Detecting Human-Object Contact in Imagescited by 41
  11. 2022D&D: Learning Human Dynamics from Dynamic Cameracited by 39
  12. 2025KungfuBot: Physics-Based Humanoid Whole-Body Control for Learning Highly-Dynamic Skillscited by 39
  13. 2021Adversarial Parametric Pose Priorcited by 38
  14. 2022Differentiable Dynamics for Articulated 3d Human Motion Reconstructioncited by 38
  15. 2022Trajectory Optimization for Physics-Based Reconstruction of 3d Human Pose from Monocular Videocited by 37
  16. 2023Skinned Motion Retargeting with Residual Perception of Motion Semantics & Geometrycited by 35
  17. 2021Task-Generic Hierarchical Human Motion Prior using VAEscited by 33
  18. 2024Beyond the Contact: Discovering Comprehensive Affordance for 3D Objects from Pre-trained 2D Diffusion Modelscited by 32
  19. 2021Contact-Aware Retargeting of Skinned Motioncited by 31
  20. 2022Neural MoCon: Neural Motion Control for Physically Plausible Human Motion Capturecited by 31
  21. 2021Gravity-Aware Monocular 3D Human-Object Reconstructioncited by 30
  22. 2022The One Where They Reconstructed 3D Humans and Environments in TV Showscited by 30
  23. 2022HULC: 3D Human Motion Capture with Pose Manifold Sampling and Dense Contact Guidancecited by 29
  24. 2024Joint Reconstruction of 3D Human and Object via Contact-Based Refinement Transformercited by 29
  25. 2021Dynamic Neural Garmentscited by 27
  26. 2024PhysPT: Physics-aware Pretrained Transformer for Estimating Human Dynamics from Monocular Videoscited by 27
  27. 2022PoseTriplet: Co-evolving 3D Human Pose Estimation, Imitation, and Hallucination under Self-supervisioncited by 25
  28. 2024PACER+: On-Demand Pedestrian Animation Controller in Driving Scenarioscited by 24
  29. 2022φ-SfT: Shape-from-Template with a Physics-Based Deformation Modelcited by 23
  30. 2023InsActor: Instruction-driven Physics-based Characterscited by 23
  31. 2022Physical Interaction: Reconstructing Hand-object Interactions with Physicscited by 19
  32. 2023CHORUS: Learning Canonicalized 3D Human-Object Spatial Relations from Unbounded Synthesized Imagescited by 19
  33. 2022MoCapDeform: Monocular 3D Human Motion Capture in Deformable Scenescited by 18
  34. 2024MoST: Motion Style Transformer between Diverse Action Contentscited by 18
  35. 2022Learning Variational Motion Prior for Video-based Motion Capturecited by 17
  36. 2023Decaf: Monocular Deformation Capture for Face and Hand Interactionscited by 17
  37. 2024Real-Time Simulated Avatar from Head-Mounted Sensorscited by 17
  38. 2024MMVP: A Multimodal MoCap Dataset with Vision and Pressure Sensorscited by 16

50 most cited of 94 All 94 (JSON)