mlsanityData to 14 Oct 2026

Diffusion Motion: Generate Text-Guided 3D Human Motion by Diffusion Model

arXiv 2210.12315 ↗First posted 22 Oct 2022cs.CVcited by 41

On the map: Diffusion models → Video generation

Abstract (arXiv)

We propose a simple and novel method for generating 3D human motion from complex natural language sentences, which describe different velocity, direction and composition of all kinds of actions. Different from existing methods that use classical generative architecture, we apply the Denoising Diffusion Probabilistic Model to this task, synthesizing diverse motion results under the guidance of texts. The diffusion model converts white noise into structured 3D motion by a Markov process with a series of denoising steps and is efficiently trained by optimizing a variational lower bound. To achieve the goal of text-conditioned image synthesis, we use the classifier-free guidance strategy to fuse text embedding into the model during training. Our experiments demonstrate that our model achieves competitive results on HumanML3D test set quantitatively and can generate more visually natural and diverse examples. We also show with experiments that our model is capable of zero-shot generation of motions for unseen text guidance.

Key facts. Cited by 41 papers in the map (data through 14 Oct 2026). Placed in Video generation, one of 14 directions in Diffusion models. Builds on 18 of its 22 references that are in the map. First posted on arXiv 22 Oct 2022.

Builds on

18 of 22 references.

References · 18

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  3. 2020Denoising Diffusion Implicit Modelscited by 9,781
  4. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  5. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,585
  6. 2022Classifier-Free Diffusion Guidancecited by 5,847
  7. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,761
  8. 2020DiffWave: A Versatile Diffusion Model for Audio Synthesiscited by 1,354
  9. 2019AMASS: Archive of Motion Capture as Surface Shapescited by 1,236
  10. 2021Diffusion Probabilistic Models for 3D Point Cloud Generationcited by 735
  11. 2017MoCoGAN: Decomposing Motion and Content for Video Generationcited by 524
  12. 2021Action-Conditioned 3D Human Motion Synthesis with Transformer VAEcited by 501
6 more
  1. 2020Action2Motion: Conditioned Generation of 3D Human Motionscited by 441
  2. 2016The KIT Motion-Language Datasetcited by 338
  3. 2019Language2Pose: Natural Language Grounded Pose Forecastingcited by 257
  4. 2021Synthesis of Compositional Animations from Textual Descriptionscited by 178
  5. 2021Text2Gestures: A Transformer-Based Network for Generating Emotive Body Gestures for Virtual Agentscited by 106
  6. 2017Deep Video Generation, Prediction and Completion of Human Action Sequencescited by 52

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 1; 2023: 14; 2024: 12; 2025: 10; 2026: 4.

41 papers.

Sort:

By area:

  1. 2022PhysDiff: Physics-Guided Human Motion Diffusion Modelcited by 368
  2. 2023CG-HOI: Contact-Guided 3D Human-Object Interaction Generationcited by 138
  3. 2023DiffuseStyleGesture: Stylized Audio-Driven Co-Speech Gesture Generation with Diffusion Modelscited by 85
  4. 2023DiffPoseTalk: Speech-Driven Stylistic 3D Facial Animation and Head Pose Generation via Diffusion Modelscited by 81
  5. 2023FaceTalk: Audio-Driven Motion Diffusion for Neural Parametric Head Modelscited by 55
  6. 2024THOR: Text to Human-Object Interaction Diffusion via Relation Interventioncited by 46
  7. 2024AnySkill: Learning Open-Vocabulary Physical Skill for Interactive Agentscited by 32
  8. 2024Motion2VecSets: 4D Latent Vector Set Diffusion for Non-rigid Shape Reconstruction and Trackingcited by 29
  9. 2023DINAR: Diffusion Inpainting of Neural Textures for One-Shot Human Avatarscited by 28
  10. 2023NAP: Neural 3D Articulation Priorcited by 25
  11. 2023ChatGPT-Powered Hierarchical Comparisons for Image Classificationcited by 22
  12. 2024HUMOS: Human Motion Model Conditioned on Body Shapecited by 20
29 more
  1. 2023Controllable Group Choreography using Contrastive Diffusioncited by 17
  2. 2023Realistic Human Motion Generation with Cross-Diffusion Modelscited by 17
  3. 2025FloodDiffusion: Tailored Diffusion Forcing for Streaming Motion Generationcited by 16
  4. 2023UnifiedGesture: A Unified Gesture Synthesis Model for Multiple Skeletonscited by 15
  5. 20233DiFACE: Diffusion-based Speech-driven 3D Facial Animation and Editingcited by 15
  6. 2025Pixel Motion as Universal Representation for Robot Controlcited by 15
  7. 2024ProbTalk3D: Non-Deterministic Emotion Controllable Speech-Driven 3D Facial Animation Synthesis Using VQ-VAEcited by 13
  8. 2024BAD: Bidirectional Auto-regressive Diffusion for Text-to-Motion Generationcited by 13
  9. 2023LongDanceDiff: Long-term Dance Generation with Conditional Diffusion Modelcited by 12
  10. 2024DEEPTalk: Dynamic Emotion Embedding for Probabilistic Speech-Driven 3D Face Animationcited by 12
  11. 2023Bipartite Graph Diffusion Model for Human Interaction Generationcited by 11
  12. 2025Shape My Moves: Text-Driven Shape-Aware Synthesis of Human Motionscited by 11
  13. 2024AVI-Talking: Learning Audio-Visual Instructions for Expressive 3D Talking Face Generationcited by 9
  14. 2024GLDiTalker: Speech-Driven 3D Facial Animation with Graph Latent Diffusion Transformercited by 8
  15. 2024Gradient-Free Classifier Guidance for Diffusion Model Samplingcited by 8
  16. 2025Pixel Motion Diffusion is What We Need for Robot Controlcited by 7
  17. 2025AnimaMimic: Imitating 3D Animation from Video Priorscited by 7
  18. 2026PersonaGesture: Single-Reference Co-Speech Gesture Personalization for Unseen Speakerscited by 7
  19. 2023AMD:Anatomical Motion Diffusion with Interpretable Motion Decomposition and Fusioncited by 5
  20. 2024Beyond Fixed Topologies: Unregistered Training and Comprehensive Evaluation Metrics for 3D Talking Headscited by 5
  21. 20253DiFACE: Synthesizing and Editing Holistic 3D Facial Animationcited by 4
  22. 2025AU-Blendshape for Fine-grained Stylized 3D Facial Expression Manipulationcited by 3
  23. 2024Diffusion-based Graph Generative Methodscited by 2
  24. 2026ReMoGen: Real-time Human Interaction-to-Reaction Generation via Modular Learning from Diverse Datacited by 1
  25. 2025Controllable Expressive 3D Facial Animation via Diffusion in a Unified Multimodal Spacecited by 0
  26. 2025Stochastic Human Motion Prediction with Memory of Action Transition and Action Characteristiccited by 0
  27. 2025Mem-MLP: Real-Time 3D Human Motion Generation from Sparse Inputscited by 0
  28. 2026InterEdit: Navigating Text-Guided 3D Dyadic Human Motion Editingcited by 0
  29. 2026Generative Data Augmentation for Skeleton Action Recognitioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023Towards Detailed Text-to-Motion Synthesis via Basic-to-Advanced Hierarchical Diffusion Model
  2. 2024M2D2M: Multi-Motion Generation from Text with Discrete Diffusion Models
  3. 2023DiffusionPhase: Motion Diffusion in Frequency Domain
  4. 2026Reconstruction-Anchored Diffusion Model for Text-to-Motion Generation
  5. 2023Priority-Centric Human Motion Generation in Discrete Latent Space
  6. 2024Text-driven Human Motion Generation with Motion Masked Diffusion Model
  7. 2024MotionMix: Weakly-Supervised Diffusion for Controllable Motion Generation
  8. 2023Synthesizing Long-Term Human Motions with Diffusion Models via Coherent Sampling