mlsanityData to 7 Oct 2026

Human Motion Diffusion Model

arXiv 2209.14916 ↗First posted 29 Sep 2022cs.CV cs.GRcited by 1,062

On the map: Diffusion models → Video generation

Abstract (arXiv)

Natural and expressive human motion generation is the holy grail of computer animation. It is a challenging task, due to the diversity of possible motion, human perceptual sensitivity to it, and the difficulty of accurately describing it. Therefore, current generative solutions are either low-quality or limited in expressiveness. Diffusion models, which have already shown remarkable generative capabilities in other domains, are promising candidates for human motion due to their many-to-many nature, but they tend to be resource hungry and hard to control. In this paper, we introduce Motion Diffusion Model (MDM), a carefully adapted classifier-free diffusion-based generative model for the human motion domain. MDM is transformer-based, combining insights from motion generation literature. A notable design-choice is the prediction of the sample, rather than the noise, in each diffusion step. This facilitates the use of established geometric losses on the locations and velocities of the motion, such as the foot contact loss. As we demonstrate, MDM is a generic approach, enabling different modes of conditioning, and different generation tasks. We show that our model is trained with lightweight resources and yet achieves state-of-the-art results on leading benchmarks for text-to-motion and action-to-motion. https://guytevet.github.io/mdm-page/ .

Key facts. Cited by 1,062 papers in the map (data through 7 Oct 2026). Placed in Video generation, one of 14 directions in Diffusion models. Builds on 43 of its 51 references that are in the map. First posted on arXiv 29 Sep 2022.

Builds on

43 of 51 references.

Closest ancestors · 3

Same direction, newest first

  1. 2022FLAME: Free-form Language-based Motion Synthesis & Editing1 Sep
  2. 2022MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model31 Aug
  3. 2022Video Diffusion Models7 Apr

Other references · 40

  1. 2017Attention Is All You Needcited by 59,932
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  4. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  5. 2020Denoising Diffusion Implicit Modelscited by 9,655
  6. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  7. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  8. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  9. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,539
  10. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,322
  11. 2022Classifier-Free Diffusion Guidancecited by 5,717
  12. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,016
28 more
  1. 2021GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Modelscited by 3,595
  2. 2019Expressive Body Capture: 3D Hands, Face, and Body from a Single Imagecited by 1,600
  3. 2021Palette: Image-to-Image Diffusion Modelscited by 1,296
  4. 2019AMASS: Archive of Motion Capture as Surface Shapescited by 1,208
  5. 2020Improved Techniques for Training Score-Based Generative Modelscited by 1,036
  6. 2021Diffusion Probabilistic Models for 3D Point Cloud Generationcited by 734
  7. 2019VIBE: Video Inference for Human Body Pose and Shape Estimationcited by 615
  8. 2021Action-Conditioned 3D Human Motion Synthesis with Transformer VAEcited by 497
  9. 2022TEMOS: Generating diverse human motions from textual descriptionscited by 486
  10. 2021AI Choreographer: Music Conditioned 3D Dance Generation with AIST++cited by 479
  11. 2020Action2Motion: Conditioned Generation of 3D Human Motionscited by 438
  12. 2022MotionCLIP: Exposing Human Motion Generation to CLIP Spacecited by 406
  13. 2017On human motion prediction using recurrent neural networkscited by 336
  14. 2016The KIT Motion-Language Datasetcited by 334
  15. 2019Language2Pose: Natural Language Grounded Pose Forecastingcited by 257
  16. 2021Robust Motion In-betweeningcited by 223
  17. 2020A Spatio-temporal Transformer for 3D Human Motion Predictioncited by 133
  18. 2020Skeleton-Aware Networks for Deep Motion Retargetingcited by 118
  19. 2018Human Motion Prediction via Spatio-Temporal Inpaintingcited by 114
  20. 2021Text2Gestures: A Transformer-Based Network for Generating Emotive Body Gestures for Virtual Agentscited by 106
  21. 2022Back to MLP: A Simple Baseline for Human Motion Predictioncited by 99
  22. 2020Convolutional Autoencoders for Human Motion Infillingcited by 73
  23. 2022Implicit Neural Representations for Variable Length Human Motion Generationcited by 61
  24. 2021Single-Shot Motion Completion with Transformercited by 59
  25. 2022MoDi: Unconditional Motion Synthesis from Diverse Datacited by 59
  26. 2021Rhythm is a Dancer: Music-Driven Motion Synthesis with Global Structurecited by 53
  27. 2018Recurrent Transition Networks for Character Locomotioncited by 52
  28. 2020MotioNet: 3D Human Motion Reconstruction from Monocular Video with Skeleton Consistencycited by 31

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 23; 2023: 200; 2024: 280; 2025: 297; 2026: 262.

1,062 papers.

Sort:

By area:

  1. 2022Objaverse: A Universe of Annotated 3D Objectscited by 1,522
  2. 2023Structure and Content-Guided Video Synthesis with Diffusion Modelscited by 589
  3. 2023T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representationscited by 577
  4. 2022Executing your Commands via Motion Diffusion in Latent Spacecited by 567
  5. 2023MultiDiffusion: Fusing Diffusion Paths for Controlled Image Generationcited by 529
  6. 2023MotionGPT: Human Motion as a Foreign Languagecited by 521
  7. 2023MoMask: Generative Masked Modeling of 3D Human Motionscited by 388
  8. 2022PhysDiff: Physics-Guided Human Motion Diffusion Modelcited by 365
  9. 2023Human Motion Diffusion as a Generative Priorcited by 354
  10. 2022EDGE: Editable Dance Generation From Musiccited by 284
  11. 2023ReMoDiffuse: Retrieval-Augmented Motion Diffusion Modelcited by 282
  12. 2023GaussianDreamer: Fast Generation from Text to 3D Gaussians by Bridging 2D and 3D Diffusion Modelscited by 255
38 more
  1. 2023Diffusion-based Generation, Optimization, and Planning in 3D Scenescited by 237
  2. 2023OmniControl: Control Any Joint at Any Time for Human Motion Generationcited by 233
  3. 2023Goal-Conditioned Imitation Learning using Score-based Diffusion Policiescited by 229
  4. 2023Michelangelo: Conditional 3D Shape Generation based on Shape-Image-Text Aligned Latent Representationcited by 225
  5. 2023Guided Motion Diffusion for Controllable Human Motion Synthesiscited by 221
  6. 2023Motion-X: A Large-scale 3D Expressive Whole-body Human Motion Datasetcited by 220
  7. 2023Habitat 3.0: A Co-Habitat for Humans, Avatars and Robotscited by 220
  8. 2022MoFusion: A Framework for Denoising-Diffusion-based Motion Synthesiscited by 218
  9. 2023Object Motion Guided Human Motion Synthesiscited by 206
  10. 2023Perpetual Humanoid Control for Real-time Simulated Avatarscited by 198
  11. 2023TMR: Text-to-Motion Retrieval Using Contrastive 3D Human Motion Synthesiscited by 194
  12. 2022Listen, Denoise, Action! Audio-Driven Motion Synthesis with Diffusion Modelscited by 188
  13. 2023InterDiff: Generating 3D Human-Object Interactions with Physics-Informed Diffusioncited by 181
  14. 2024Agent AI: Surveying the Horizons of Multimodal Interactioncited by 167
  15. 2024MotionLCM: Real-time Controllable Motion Generation via Latent Consistency Modelcited by 164
  16. 2023GestureDiffuCLIP: Gesture Diffusion Model with CLIP Latentscited by 156
  17. 2023HyperDiffusion: Generating Implicit Neural Fields with Weight-Space Diffusioncited by 152
  18. 2023MotionGPT: Finetuned LLMs Are General-Purpose Motion Generatorscited by 145
  19. 2023CG-HOI: Contact-Guided 3D Human-Object Interaction Generationcited by 137
  20. 2024Scaling Up Dynamic Human-Scene Interaction Modelingcited by 137
  21. 2023MMM: Generative Masked Motion Modelcited by 129
  22. 2025BeyondMimic: From Motion Tracking to Versatile Humanoid Control via Guided Diffusioncited by 128
  23. 2024World-Grounded Human Motion Recovery via Gravity-View Coordinatescited by 127
  24. 2023State of the Art on Diffusion Models for Visual Computingcited by 126
  25. 2023CADS: Unleashing the Diversity of Diffusion Models through Condition-Annealed Samplingcited by 124
  26. 2023Understanding the Latent Space of Diffusion Models through the Lens of Riemannian Geometrycited by 121
  27. 2024Expressive Whole-Body Control for Humanoid Robotscited by 117
  28. 2023AttT2M: Text-Driven Human Motion Generation with Multi-Perspective Attention Mechanismcited by 116
  29. 2024Motion Mamba: Efficient and Long Sequence Motion Generationcited by 111
  30. 2023Synthesizing Diverse Human Motions in 3D Indoor Scenescited by 109
  31. 2023TADA! Text to Animatable Digital Avatarscited by 109
  32. 2024Nymeria: A Massive Collection of Multimodal Egocentric Daily Motion in the Wildcited by 109
  33. 2023Controllable Human-Object Interaction Synthesiscited by 107
  34. 2023FineMoGen: Fine-Grained Spatio-Temporal Motion Generation and Editingcited by 105
  35. 2023Avatars Grow Legs: Generating Smooth Human Motion from Sparse Tracking Inputs with Diffusion Modelcited by 104
  36. 2023HumanTOMATO: Text-aligned Whole-body Motion Generationcited by 103
  37. 2024CLoSD: Closing the Loop between Simulation and Diffusion for multi-task character controlcited by 103
  38. 2023DreamHuman: Animatable 3D Avatars from Textcited by 102

50 most cited of 1,062 All 1,062 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2022Unifying Human Motion Synthesis and Style Transfer with Denoising Diffusion Probabilistic Models
  2. 2024Human Motion Synthesis_ A Diffusion Approach for Motion Stitching and In-Betweening
  3. 2025Strong and Controllable 3D Motion Generation
  4. 2022Denoising Diffusion Probabilistic Models for Styled Walking Synthesis
  5. 2024MotionMix: Weakly-Supervised Diffusion for Controllable Motion Generation
  6. 2023AMD: Autoregressive Motion Diffusion
  7. 2024DivDiff: A Conditional Diffusion Model for Diverse Human Motion Prediction
  8. 2024UniAnimate: Taming Unified Video Diffusion Models for Consistent Human Image Animation