mlsanityData to 7 Oct 2026

PhysDiff: Physics-Guided Human Motion Diffusion Model

arXiv 2212.02500 ↗First posted 5 Dec 2022cs.CV cs.AI cs.GRcited by 365

On the map: Diffusion models → Video generation

Abstract (arXiv)

Denoising diffusion models hold great promise for generating diverse and realistic human motions. However, existing motion diffusion models largely disregard the laws of physics in the diffusion process and often generate physically-implausible motions with pronounced artifacts such as floating, foot sliding, and ground penetration. This seriously impacts the quality of generated motions and limits their real-world application. To address this issue, we present a novel physics-guided motion diffusion model (PhysDiff), which incorporates physical constraints into the diffusion process. Specifically, we propose a physics-based motion projection module that uses motion imitation in a physics simulator to project the denoised motion of a diffusion step to a physically-plausible motion. The projected motion is further used in the next diffusion step to guide the denoising diffusion process. Intuitively, the use of physics in our model iteratively pulls the motion toward a physically-plausible space, which cannot be achieved by simple post-processing. Experiments on large-scale human motion datasets show that our approach achieves state-of-the-art motion quality and improves physical plausibility drastically (>78% for all datasets).

Key facts. Cited by 365 papers in the map (data through 7 Oct 2026). Placed in Video generation, one of 14 directions in Diffusion models. Builds on 75 of its 102 references that are in the map. First posted on arXiv 5 Dec 2022.

Builds on

75 of 102 references.

Closest ancestors · 3

Same direction, newest first

  1. 2022Diffusion Motion: Generate Text-Guided 3D Human Motion by Diffusion Model22 Oct
  2. 2022Human Motion Diffusion Model29 Sep
  3. 2022MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model31 Aug

Other references · 72

  1. 2017Attention Is All You Needcited by 59,932
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  4. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  5. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  6. 2017Proximal Policy Optimization Algorithmscited by 14,441
  7. 2020Denoising Diffusion Implicit Modelscited by 9,655
  8. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  9. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  10. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  11. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,539
  12. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,322
38 more
  1. 2022Classifier-Free Diffusion Guidancecited by 5,717
  2. 2022Elucidating the Design Space of Diffusion-Based Generative Modelscited by 2,994
  3. 2022DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Stepscited by 1,961
  4. 2015High-Dimensional Continuous Control Using Generalized Advantage Estimationcited by 1,916
  5. 2021SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equationscited by 1,903
  6. 2022RePaint: Inpainting using Denoising Diffusion Probabilistic Modelscited by 1,419
  7. 2020DiffWave: A Versatile Diffusion Model for Audio Synthesiscited by 1,339
  8. 2019AMASS: Archive of Motion Capture as Surface Shapescited by 1,208
  9. 2021Variational Diffusion Modelscited by 1,145
  10. 2022Denoising Diffusion Restoration Modelscited by 951
  11. 2021Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learningcited by 882
  12. 2021Diffusion Probabilistic Models for 3D Point Cloud Generationcited by 734
  13. 2022Pseudo Numerical Methods for Diffusion Models on Manifoldscited by 695
  14. 2020NVAE: A Deep Hierarchical Variational Autoencodercited by 635
  15. 2021Score-based Generative Modeling in Latent Spacecited by 634
  16. 2021ILVR: Conditioning Method for Denoising Diffusion Probabilistic Modelscited by 634
  17. 2022LION: Latent Point Diffusion Models for 3D Shape Generationcited by 552
  18. 2022Fast Sampling of Diffusion Models with Exponential Integratorcited by 526
  19. 20213D Shape Generation and Completion through Point-Voxel Diffusioncited by 516
  20. 2021Action-Conditioned 3D Human Motion Synthesis with Transformer VAEcited by 497
  21. 2022TEMOS: Generating diverse human motions from textual descriptionscited by 486
  22. 2021AI Choreographer: Music Conditioned 3D Dance Generation with AIST++cited by 479
  23. 2022Diffusion Models for Adversarial Purificationcited by 469
  24. 2020Action2Motion: Conditioned Generation of 3D Human Motionscited by 438
  25. 2017On human motion prediction using recurrent neural networkscited by 336
  26. 2022Analytic-DPM: an Analytic Estimate of the Optimal Reverse Variance in Diffusion Probabilistic Modelscited by 331
  27. 2021Come-Closer-Diffuse-Faster: Accelerating Conditional Diffusion Models for Inverse Problems through Stochastic Contractioncited by 306
  28. 2019Language2Pose: Natural Language Grounded Pose Forecastingcited by 257
  29. 2019Learning Trajectory Dependencies for Human Motion Predictioncited by 245
  30. 2021Score-Based Generative Modeling with Critically-Damped Langevin Diffusioncited by 230
  31. 2021SNIPS: Solving Noisy Inverse Problems Stochasticallycited by 191
  32. 2020DLow: Diversifying Latent Flows for Diverse Human Motion Predictioncited by 184
  33. 2017HP-GAN: Probabilistic 3D human motion prediction via GANcited by 176
  34. 2022Physical Inertial Poser (PIP): Physics-aware Real-time Human Motion Tracking from Sparse Inertial Sensorscited by 144
  35. 2022GENIE: Higher-Order Denoising Diffusion Solverscited by 127
  36. 2022gDDIM: Generalized denoising diffusion implicit modelscited by 125
  37. 2021DanceFormer: Music Conditioned 3D Dance Generation with Parametric Motion Transformercited by 111
  38. 2021SimPoE: Simulated Character Control for 3D Human Pose Estimationcited by 111

50 most cited of 72 All 72 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 65; 2024: 109; 2025: 117; 2026: 74.

365 papers.

Sort:

By area:

  1. 2023MultiDiffusion: Fusing Diffusion Paths for Controlled Image Generationcited by 529
  2. 2023Human Motion Diffusion as a Generative Priorcited by 354
  3. 2023OmniControl: Control Any Joint at Any Time for Human Motion Generationcited by 233
  4. 2023Guided Motion Diffusion for Controllable Human Motion Synthesiscited by 221
  5. 2023Motion-X: A Large-scale 3D Expressive Whole-body Human Motion Datasetcited by 220
  6. 2024VideoPhy: Evaluating Physical Commonsense for Video Generationcited by 215
  7. 2023InterGen: Diffusion-based Multi-human Motion Generation under Complex Interactionscited by 205
  8. 2023Perpetual Humanoid Control for Real-time Simulated Avatarscited by 198
  9. 2023InterDiff: Generating 3D Human-Object Interactions with Physics-Informed Diffusioncited by 181
  10. 2024Motion Prompting: Controlling Video Generation with Motion Trajectoriescited by 176
  11. 2023Align Your Gaussians: Text-to-4D with Dynamic 3D Gaussians and Composed Diffusion Modelscited by 169
  12. 2024MotionLCM: Real-time Controllable Motion Generation via Latent Consistency Modelcited by 164
38 more
  1. 2023CG-HOI: Contact-Guided 3D Human-Object Interaction Generationcited by 137
  2. 2023State of the Art on Diffusion Models for Visual Computingcited by 126
  3. 2024PhyScene: Physically Interactable 3D Scene Synthesis for Embodied AIcited by 116
  4. 2023Synthesizing Diverse Human Motions in 3D Indoor Scenescited by 109
  5. 2023Universal Humanoid Motion Representations for Physics-Based Controlcited by 109
  6. 2023Controllable Human-Object Interaction Synthesiscited by 107
  7. 2023HumanTOMATO: Text-aligned Whole-body Motion Generationcited by 103
  8. 2024CLoSD: Closing the Loop between Simulation and Diffusion for multi-task character controlcited by 103
  9. 2023Optimizing Diffusion Noise Can Serve As Universal Motion Priorscited by 97
  10. 2023PreDiff: Precipitation Nowcasting with Latent Diffusion Modelscited by 96
  11. 2025Being-H0: Vision-Language-Action Pretraining from Large-Scale Human Videoscited by 94
  12. 2023TLControl: Trajectory and Language Control for Human Motion Synthesiscited by 93
  13. 2023EMDM: Efficient Motion Diffusion Model for Fast and High-Quality Motion Generationcited by 88
  14. 2024Physics-Informed Diffusion Modelscited by 88
  15. 2023DiffuseStyleGesture: Stylized Audio-Driven Co-Speech Gesture Generation with Diffusion Modelscited by 85
  16. 2024Constrained Synthesis with Projected Diffusion Modelscited by 83
  17. 2024Rethinking Diffusion for Text-Driven Human Motion Generation: Redundant Representations, Evaluation, and Masked Autoregressioncited by 78
  18. 2024Seamless Human Motion Composition with Blended Positional Encodingscited by 77
  19. 2023SafeDiffuser: Safe Planning with Diffusion Probabilistic Modelscited by 69
  20. 2024Flexible Motion In-betweening with Diffusion Modelscited by 69
  21. 2025Go to Zero: Towards Zero-shot Motion Generation with Million-scale Datacited by 67
  22. 2024CoMo: Controllable Motion Generation through Language Guided Pose Code Editingcited by 66
  23. 2024A Survey on Diffusion Models for Time Series and Spatio-Temporal Datacited by 66
  24. 2023Single Motion Diffusioncited by 65
  25. 2024Large Motion Model for Unified Multi-Modal Motion Generationcited by 65
  26. 2023AvatarGPT: All-in-One Framework for Motion Understanding, Planning, Generation and Beyondcited by 63
  27. 2023ReMoS: 3D Motion-Conditioned Reaction Synthesis for Two-Person Interactionscited by 62
  28. 2024DiffH2O: Diffusion-Based Synthesis of Hand-Object Interactions from Textual Descriptionscited by 60
  29. 2023MoConVQ: Unified Physics-Based Motion Control via Scalable Discrete Representationscited by 58
  30. 2024LaMP: Language-Motion Pretraining for Motion Generation, Retrieval, and Captioningcited by 58
  31. 2024Taming Diffusion Probabilistic Models for Character Controlcited by 56
  32. 2023Interactive Character Control with Auto-Regressive Motion Diffusion Modelscited by 52
  33. 2024ScaMo: Exploring the Scaling Law in Autoregressive Motion Generation Modelcited by 52
  34. 2024On the Trajectory Regularity of ODE-based Diffusion Samplingcited by 51
  35. 2025VLIPP: Towards Physically Plausible Video Generation with Vision and Language Informed Physical Priorcited by 49
  36. 2023TEDi: Temporally-Entangled Diffusion for Long-Term Motion Synthesiscited by 48
  37. 2024StableMoFusion: Towards Robust and Efficient Diffusion-based Motion Generation Frameworkcited by 48
  38. 2023OMG: Towards Open-vocabulary Motion Generation via Mixture of Controllerscited by 47

50 most cited of 365 All 365 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2022Human Joint Kinematics Diffusion-Refinement for Stochastic Motion Prediction
  2. 2023R2-Diff: Denoising by diffusion as a refinement of retrieved motion for image-based motion prediction
  3. 2023BoDiffusion: Diffusing Sparse Observations for Full-Body Human Motion Synthesis
  4. 2024MotionMix: Weakly-Supervised Diffusion for Controllable Motion Generation
  5. 2025Nonisotropic Gaussian Diffusion for Realistic 3D Human Motion Prediction
  6. 2022Unifying Human Motion Synthesis and Style Transfer with Denoising Diffusion Probabilistic Models
  7. 2022Denoising Diffusion Probabilistic Models for Styled Walking Synthesis
  8. 2023Denoising Heat-inspired Diffusion with Insulators for Collision Free Motion Planning