mlsanityData to 7 Oct 2026

HUMOS: Human Motion Model Conditioned on Body Shape

arXiv 2409.03944 ↗First posted 5 Sep 2024cs.CV cs.AIcited by 20

Not on the map. Why?

Abstract (arXiv)

Generating realistic human motion is essential for many computer vision and graphics applications. The wide variety of human body shapes and sizes greatly impacts how people move. However, most existing motion models ignore these differences, relying on a standardized, average body. This leads to uniform motion across different body types, where movements don't match their physical characteristics, limiting diversity. To solve this, we introduce a new approach to develop a generative motion model based on body shape. We show that it's possible to train this model using unpaired data by applying cycle consistency, intuitive physics, and stability constraints, which capture the relationship between identity and movement. The resulting model generates diverse, physically plausible, and dynamically stable human motions that are both quantitatively and qualitatively more realistic than current state-of-the-art methods. More details are available on our project page https://CarstenEpic.github.io/humos/.

Key facts. Cited by 20 papers in the map (data through 7 Oct 2026). Builds on 51 of its 86 references that are in the map. First posted on arXiv 5 Sep 2024.

Builds on

51 of 86 references.

References · 51

  1. 2017Attention Is All You Needcited by 59,932
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2017Proximal Policy Optimization Algorithmscited by 14,441
  4. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  5. 2015High-Dimensional Continuous Control Using Generalized Advantage Estimationcited by 1,916
  6. 2019AMASS: Archive of Motion Capture as Surface Shapescited by 1,208
  7. 2018On the Continuity of Rotation Representations in Neural Networkscited by 1,186
  8. 2022Human Motion Diffusion Modelcited by 1,062
  9. 2021Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learningcited by 882
  10. 2022MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Modelcited by 768
  11. 2021ILVR: Conditioning Method for Denoising Diffusion Probabilistic Modelscited by 634
  12. 2022Executing your Commands via Motion Diffusion in Latent Spacecited by 567
38 more
  1. 2021Action-Conditioned 3D Human Motion Synthesis with Transformer VAEcited by 497
  2. 2022TEMOS: Generating diverse human motions from textual descriptionscited by 486
  3. 2021AI Choreographer: Music Conditioned 3D Dance Generation with AIST++cited by 479
  4. 2020Action2Motion: Conditioned Generation of 3D Human Motionscited by 438
  5. 2022PhysDiff: Physics-Guided Human Motion Diffusion Modelcited by 365
  6. 2022Analytic-DPM: an Analytic Estimate of the Optimal Reverse Variance in Diffusion Probabilistic Modelscited by 331
  7. 2021HuMoR: 3D Human Motion Model for Robust Pose Estimationcited by 319
  8. 2019Language2Pose: Natural Language Grounded Pose Forecastingcited by 257
  9. 2019Learning Individual Styles of Conversational Gesturecited by 190
  10. 2020DLow: Diversifying Latent Flows for Diverse Human Motion Predictioncited by 184
  11. 2021Synthesis of Compositional Animations from Textual Descriptionscited by 177
  12. 2017HP-GAN: Probabilistic 3D human motion prediction via GANcited by 176
  13. 2022TEACH: Temporal Action Composition for 3D Humanscited by 173
  14. 2022Physical Inertial Poser (PIP): Physics-aware Real-time Human Motion Tracking from Sparse Inertial Sensorscited by 144
  15. 2021GOAL: Generating 4D Whole-Body Motion for Hand-Object Graspingcited by 142
  16. 2022GENIE: Higher-Order Denoising Diffusion Solverscited by 127
  17. 2020Skeleton-Aware Networks for Deep Motion Retargetingcited by 118
  18. 2021DanceFormer: Music Conditioned 3D Dance Generation with Parametric Motion Transformercited by 111
  19. 2021SimPoE: Simulated Character Control for 3D Human Pose Estimationcited by 111
  20. 2017Text2Action: Generative Adversarial Synthesis from Language to Actioncited by 106
  21. 2021Text2Gestures: A Transformer-Based Network for Generating Emotive Body Gestures for Virtual Agentscited by 106
  22. 20233D Human Pose Estimation via Intuitive Physicscited by 100
  23. 2019Structured Prediction Helps 3D Human Motion Modellingcited by 96
  24. 2018A Neural Temporal Model for Human Motion Predictioncited by 87
  25. 2020Learning to Generate Diverse Dance Motions with Transformercited by 85
  26. 2022Estimating the Optimal Covariance with Imperfect Mean in Diffusion Probabilistic Modelscited by 83
  27. 2021Neural Monocular 3D Human Motion Capture with Physical Awarenesscited by 70
  28. 2017Learning Human Motion Models for Long-term Predictionscited by 67
  29. 2022NeMF: Neural Motion Fields for Kinematic Animationcited by 66
  30. 2020Residual Force Control for Agile Human Behavior Imitation and Extended Motion Synthesiscited by 63
  31. 2023SINC: Spatial Composition of 3D Human Motions for Simultaneous Action Generationcited by 62
  32. 2020Unsupervised Shape and Pose Disentanglement for 3D Meshescited by 61
  33. 2021Speech2AffectiveGestures: Synthesizing Co-Speech Gestures with Generative Adversarial Affective Expression Learningcited by 58
  34. 2016Learning Locomotion Skills Using DeepRL: Does the Choice of Action Space Matter?cited by 44
  35. 2019Learning Character-Agnostic Motion for Motion Retargeting in 2Dcited by 44
  36. 2022Diffusion Motion: Generate Text-Guided 3D Human Motion by Diffusion Modelcited by 41
  37. 2020Neural Pose Transfer by Spatially Adaptive Instance Normalizationcited by 37
  38. 2023Skinned Motion Retargeting with Residual Perception of Motion Semantics & Geometrycited by 35

50 most cited of 51 All 51 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 10; 2026: 8.

20 papers.

Sort:

By area:

  1. 2024Rethinking Diffusion for Text-Driven Human Motion Generation: Redundant Representations, Evaluation, and Masked Autoregressioncited by 78
  2. 2025AnyTop: Character Animation Diffusion with Any Topologycited by 37
  3. 2025Absolute Coordinates Make Motion Generation Easycited by 27
  4. 2025REWIND: Real-Time Egocentric Whole-Body Motion Diffusion with Exemplar-Based Identity Conditioningcited by 14
  5. 2025PRIMAL: Physically Reactive and Interactive Motor Model for Avatar Learningcited by 13
  6. 2025Shape My Moves: Text-Driven Shape-Aware Synthesis of Human Motionscited by 11
  7. 2025GAITGen: Disentangled Motion-Pathology Impaired Gait Generative Model -- Bringing Motion Generation to the Clinical Domaincited by 7
  8. 2024Learning to Generate Diverse Pedestrian Movements from Web Videos with Noisy Labelscited by 4
  9. 2025Multi-Embodiment Robotic Retargeting via Guided Diffusion Modelcited by 3
  10. 2025OmniMotion-X: Versatile Multimodal Whole-Body Motion Generationcited by 2
  11. 2025MMCM: Multimodality-aware Metric using Clustering-based Modes for Probabilistic Human Motion Predictioncited by 1
  12. 2026IAM: Identity-Aware Human Motion and Shape Joint Generationcited by 1
8 more
  1. 2026InterPhys: Physics-aware Human Motion Synthesis in a Dynamic Scenecited by 1
  2. 2026Self-Intersection-Aware 3D Human Motion Generation Using an Efficient Human Sphere Proxycited by 1
  3. 2025Improving Human Motion Plausibility with Body Momentumcited by 0
  4. 2026HARMONI: Aligning Human and Scene Priors for Multi-View 4D Reconstructioncited by 0
  5. 2026UniCon3R: Unified Contact-aware 4D Human-Scene Reconstruction from Monocular Videocited by 0
  6. 2026Odoriko: A Shape-Aware Multimodal Diffusion Framework for Human Motioncited by 0
  7. 2026Text Dictates, Music Decorates: Energy-based Attention for Editable Dance Motion Generationcited by 0
  8. 2026LYRIC: Language-Driven Physics-Based Character Control for Contact-Rich Whole-Body Object Interactioncited by 0