mlsanityData to 14 Oct 2026

3D Human Pose Estimation via Intuitive Physics

arXiv 2303.18246 ↗First posted 31 Mar 2023cs.CV cs.AI cs.GRcited by 103

Not on the map. Why?

Abstract (arXiv)

Estimating 3D humans from images often produces implausible bodies that lean, float, or penetrate the floor. Such methods ignore the fact that bodies are typically supported by the scene. A physics engine can be used to enforce physical plausibility, but these are not differentiable, rely on unrealistic proxy bodies, and are difficult to integrate into existing optimization and learning frameworks. In contrast, we exploit novel intuitive-physics (IP) terms that can be inferred from a 3D SMPL body interacting with the scene. Inspired by biomechanics, we infer the pressure heatmap on the body, the Center of Pressure (CoP) from the heatmap, and the SMPL body's Center of Mass (CoM). With these, we develop IPMAN, to estimate a 3D body from a color image in a "stable" configuration by encouraging plausible floor contact and overlapping CoP and CoM. Our IP terms are intuitive, easy to implement, fast to compute, differentiable, and can be integrated into existing optimization and regression methods. We evaluate IPMAN on standard datasets and MoYo, a new dataset with synchronized multi-view images, ground-truth 3D bodies with complex poses, body-floor contact, CoM and pressure. IPMAN produces more plausible results than the state of the art, improving accuracy for static poses, while not hurting dynamic ones. Code and data are available for research at https://ipman.is.tue.mpg.de.

Key facts. Cited by 103 papers in the map (data through 14 Oct 2026). Builds on 73 of its 124 references that are in the map. First posted on arXiv 31 Mar 2023.

Builds on

73 of 124 references.

References · 73

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  2. 2019Expressive Body Capture: 3D Hands, Face, and Body from a Single Imagecited by 1,612
  3. 2019AMASS: Archive of Motion Capture as Surface Shapescited by 1,236
  4. 2018On the Continuity of Rotation Representations in Neural Networkscited by 1,214
  5. 2018OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,162
  6. 2017End-to-end Recovery of Human Shape and Posecited by 885
  7. 2016Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Imagecited by 695
  8. 2019Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loopcited by 627
  9. 2019VIBE: Video Inference for Human Body Pose and Shape Estimationcited by 620
  10. 2019MediaPipe: A Framework for Building Perception Pipelinescited by 583
  11. 2018DensePose: Dense Human Pose Estimation In The Wildcited by 575
  12. 2016Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervisioncited by 494
38 more
  1. 2020End-to-End Human Pose and Mesh Reconstruction with Transformerscited by 418
  2. 2019Learning joint reconstruction of hands and manipulated objectscited by 378
  3. 2021PARE: Part Attention Regressor for 3D Human Body Estimationcited by 337
  4. 2021HuMoR: 3D Human Motion Model for Robust Pose Estimationcited by 324
  5. 2018Learning 3D Human Dynamics from Videocited by 316
  6. 2022ARCTIC: A Dataset for Dexterous Bimanual Hand-Object Manipulationcited by 312
  7. 2020HybrIK: A Hybrid Analytical-Neural Inverse Kinematics Solution for 3D Human Pose and Shape Estimationcited by 307
  8. 2019Resolving 3D Human Pose Ambiguities with 3D Scene Constraintscited by 295
  9. 2020I2L-MeshNet: Image-to-Lixel Prediction Network for Accurate 3D Human Pose and Mesh Estimation from a Single RGB Imagecited by 274
  10. 2019Convolutional Mesh Regression for Single-Image Human Shape Reconstructioncited by 270
  11. 2021PyMAF: 3D Human Pose and Shape Regression with Pyramidal Mesh Alignment Feedback Loopcited by 250
  12. 2018Total Capture: A 3D Deformation Model for Tracking Faces, Hands, and Bodiescited by 239
  13. 2022CLIFF: Carrying Location Information in Full Frames into Human Pose and Shape Estimationcited by 238
  14. 2020Monocular, One-stage, Regression of Multiple 3D Peoplecited by 218
  15. 2020Deep Learning-Based Human Pose Estimation: A Surveycited by 207
  16. 2021AGORA: Avatars in Geography Optimized for Regression Analysiscited by 205
  17. 2022ECON: Explicit Clothed humans Optimized via Normal integrationcited by 199
  18. 2022Capturing and Inferring Dense Full-Body Human-Scene Contactcited by 180
  19. 2021FrankMocap: A Monocular 3D Whole-Body Pose Estimation System via Regression and Integrationcited by 169
  20. 2020Populating 3D Scenes by Learning Human-Scene Interactioncited by 164
  21. 2018DeepMimic: Example-Guided Deep Reinforcement Learning of Physics-Based Character Skillscited by 163
  22. 2018Monocular Total Capture: Posing Face, Body, and Hands in the Wildcited by 162
  23. 2020Monocular Expressive Body Regression through Body-Driven Attentioncited by 155
  24. 2021SMPLicit: Topology-aware Generative Model for Clothed Peoplecited by 155
  25. 2021GLAMR: Global Occlusion-Aware Human Mesh Recovery with Dynamic Camerascited by 153
  26. 2020Perceiving 3D Human-Object Spatial Arrangements from a Single Image in the Wildcited by 152
  27. 2021Collaborative Regression of Expressive Bodies using Moderationcited by 137
  28. 2020Coherent Reconstruction of Multiple Humans from a Single Imagecited by 136
  29. 2021SPEC: Seeing People in the Wild with an Estimated Cameracited by 135
  30. 2017VNect: Real-time 3D Human Pose Estimation with a Single RGB Cameracited by 129
  31. 2015Capturing Hands in Action using Discriminative Salient Points and Physics Simulationcited by 115
  32. 2021SimPoE: Simulated Character Control for 3D Human Pose Estimationcited by 114
  33. 2022Recovering 3D Human Mesh from Monocular Images: A Surveycited by 103
  34. 2021Learning Motion Priors for 4D Human Body Capture in 3D Scenescited by 98
  35. 2020Contact and Human Dynamics from Monocular Videocited by 95
  36. 2022CHORE: Contact, Human and Object REconstruction from a single RGB imagecited by 95
  37. 2020Weakly Supervised 3D Human Pose and Shape Reconstruction with Normalizing Flowscited by 94
  38. 2021On Self-Contact and Human Posecited by 89

50 most cited of 73 All 73 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 8; 2024: 28; 2025: 32; 2026: 35.

103 papers.

Sort:

By area:

  1. 2024TokenHMR: Advancing Human Mesh Recovery with a Tokenized Pose Representationcited by 95
  2. 2023TRACE: 5D Temporal Regression of Avatars with Dynamic Cameras in 3D Environmentscited by 91
  3. 2024Neural Localizer Fields for Continuous 3D Human Pose and Shape Estimationcited by 59
  4. 2023DECO: Dense Estimation of 3D Human-Scene Contact In The Wildcited by 54
  5. 2025KungfuBot: Physics-Based Humanoid Whole-Body Control for Learning Highly-Dynamic Skillscited by 52
  6. 2024AnySkill: Learning Open-Vocabulary Physical Skill for Interactive Agentscited by 32
  7. 2025SMPLest-X: Ultimate Scaling for Expressive Human Pose and Shape Estimationcited by 32
  8. 2025AnimateAnyMesh: A Feed-Forward 4D Foundation Model for Text-Driven Universal Mesh Animationcited by 32
  9. 2023Dynamic Inertial Poser (DynaIP): Part-Based Motion Dynamics Learning for Enhanced Human Pose Estimation with Sparse Inertial Sensorscited by 30
  10. 2024PhysPT: Physics-aware Pretrained Transformer for Estimating Human Dynamics from Monocular Videoscited by 28
  11. 2025From Skin to Skeleton: Towards Biomechanically Accurate 3D Digital Humanscited by 27
  12. 2024HMD-Poser: On-Device Real-time Human Motion Tracking from Scalable Sparse Observationscited by 25
38 more
  1. 2025BEDLAM2.0: Synthetic Humans and Cameras in Motioncited by 25
  2. 2025Reconstructing Humans with a Biomechanically Accurate Skeletoncited by 22
  3. 2025PICO: Reconstructing 3D People In Contact with Objectscited by 22
  4. 2024HUMOS: Human Motion Model Conditioned on Body Shapecited by 20
  5. 2024UniPose: A Unified Multimodal Framework for Human Pose Comprehension, Generation and Editingcited by 18
  6. 2025From Language to Locomotion: Retargeting-free Humanoid Control via Motion Latent Guidancecited by 18
  7. 2024MMVP: A Multimodal MoCap Dataset with Vision and Pressure Sensorscited by 17
  8. 2024A Unified Diffusion Framework for Scene-aware Human Motion Estimation from Sparse Signalscited by 16
  9. 2024MEGA: Masked Generative Autoencoder for Human Mesh Recoverycited by 14
  10. 2025Reconstructing 4D Spatial Intelligence: A Surveycited by 14
  11. 2023Reconstructing Signing Avatars From Video Using Linguistic Priorscited by 12
  12. 2024AWOL: Analysis WithOut synthesis using Languagecited by 12
  13. 2024ChatHuman: Chatting about 3D Humans with Toolscited by 11
  14. 2025Shape My Moves: Text-Driven Shape-Aware Synthesis of Human Motionscited by 11
  15. 2023Physics-guided Shape-from-Template: Monocular Video Perception through Neural Surrogate Modelscited by 8
  16. 2024Diffusion Models are Efficient Data Generators for Human Mesh Recoverycited by 8
  17. 2024Textual Decomposition Then Sub-motion-space Scattering for Open-Vocabulary Motion Generationcited by 8
  18. 2024FORCE: Physics-aware Human-object Interactioncited by 7
  19. 2024OpenCapBench: A Benchmark to Bridge Pose Estimation and Biomechanicscited by 7
  20. 2025PhysHMR: Learning Humanoid Control Policies from Vision for Physically Plausible Human Motion Reconstructioncited by 7
  21. 2024UPose3D: Uncertainty-Aware 3D Human Pose Estimation with Cross-View and Temporal Cuescited by 6
  22. 2024Pose Priors from Language Modelscited by 6
  23. 20243D Whole-body Grasp Synthesis with Directional Controllabilitycited by 6
  24. 2024Optimal-state Dynamics Estimation for Physics-based Human Motion Capture from Videoscited by 6
  25. 2025PoissonNet: A Local-Global Approach for Learning on Surfacescited by 6
  26. 2024A Plug-and-Play Physical Motion Restoration Approach for In-the-Wild High-Difficulty Motionscited by 5
  27. 2025Diffusion-based 3D Hand Motion Recovery with Intuitive Physicscited by 5
  28. 2023GraMMaR: Ground-aware Motion Model for 3D Human Motion Reconstructioncited by 4
  29. 2025Mojito: LLM-Aided Motion Instructor with Jitter-Reduced Inertial Tokenscited by 4
  30. 2023W-HMR: Monocular Human Mesh Recovery in World Space with Weak-Supervised Calibrationcited by 3
  31. 2024MoCap-to-Visual Domain Adaptation for Efficient Human Mesh Estimation from 2D Keypointscited by 3
  32. 2025AJAHR: Amputated Joint Aware 3D Human Mesh Recoverycited by 3
  33. 2026QuaMo: Quaternion Motions for Vision-based 3D Human Kinematics Capturecited by 3
  34. 2026NymeriaPlus: Enriching Nymeria Dataset with Additional Annotations and Datacited by 3
  35. 2026HumanScore: Benchmarking Human Motions in Generated Videoscited by 3
  36. 2024SkelFormer: Markerless 3D Pose and Shape Estimation using Skeletal Transformerscited by 2
  37. 2024Di2Pose: Discrete Diffusion Model for Occluded 3D Human Pose Estimationcited by 2
  38. 2024Towards Unstructured Unlabeled Optical Mocap: A Video Helps!cited by 2

50 most cited of 103 All 103 (JSON)