mlsanityData to 14 Oct 2026

Motion Flow Matching for Human Motion Synthesis and Editing

arXiv 2312.08895 ↗First posted 14 Dec 2023cs.CVcited by 38

On the map: Diffusion models → Video generation

Abstract (arXiv)

Human motion synthesis is a fundamental task in computer animation. Recent methods based on diffusion models or GPT structure demonstrate commendable performance but exhibit drawbacks in terms of slow sampling speeds and error accumulation. In this paper, we propose Motion Flow Matching, a novel generative model designed for human motion generation featuring efficient sampling and effectiveness in motion editing applications. Our method reduces the sampling complexity from thousand steps in previous diffusion models to just ten steps, while achieving comparable performance in text-to-motion and action-to-motion generation benchmarks. Noticeably, our approach establishes a new state-of-the-art Fr'echet Inception Distance on the KIT-ML dataset. What is more, we tailor a straightforward motion editing paradigm named sampling trajectory rewriting leveraging the ODE-style generative models and apply it to various editing scenarios including motion prediction, motion in-between prediction, motion interpolation, and upper-body editing. Our code will be released.

Key facts. Cited by 38 papers in the map (data through 14 Oct 2026). Placed in Video generation, one of 14 directions in Diffusion models. Builds on 58 of its 69 references that are in the map. First posted on arXiv 14 Dec 2023.

Builds on

58 of 69 references.

Closest ancestors · 6

Same direction, newest first

  1. 2023Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models18 Apr
  2. 2023ReMoDiffuse: Retrieval-Augmented Motion Diffusion Model3 Apr
  3. 2022Executing your Commands via Motion Diffusion in Latent Space8 Dec
  4. 2022Human Motion Diffusion Model29 Sep
  5. 2022MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model31 Aug
  6. 2022Video Diffusion Models7 Apr

Other references · 52

  1. 2017Attention Is All You Needcited by 60,361
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  3. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  4. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  5. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  6. 2020Denoising Diffusion Implicit Modelscited by 9,781
  7. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  8. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  9. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,355
  10. 2022Classifier-Free Diffusion Guidancecited by 5,847
  11. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,761
  12. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,700
38 more
  1. 2022FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awarenesscited by 3,673
  2. 2022Elucidating the Design Space of Diffusion-Based Generative Modelscited by 3,045
  3. 2022Prompt-to-Prompt Image Editing with Cross Attention Controlcited by 2,431
  4. 2022DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Stepscited by 1,979
  5. 2021SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equationscited by 1,937
  6. 2023Consistency Modelscited by 1,822
  7. 2019Expressive Body Capture: 3D Hands, Face, and Body from a Single Imagecited by 1,612
  8. 2019AMASS: Archive of Motion Capture as Surface Shapescited by 1,236
  9. 2022Null-text Inversion for Editing Real Images using Guided Diffusion Modelscited by 1,179
  10. 2021Variational Diffusion Modelscited by 1,153
  11. 2022Building Normalizing Flows with Stochastic Interpolantscited by 995
  12. 2021Diffusion Probabilistic Models for 3D Point Cloud Generationcited by 735
  13. 2022Pseudo Numerical Methods for Diffusion Models on Manifoldscited by 700
  14. 2021ILVR: Conditioning Method for Denoising Diffusion Probabilistic Modelscited by 635
  15. 2023AudioLDM: Text-to-Audio Generation with Latent Diffusion Modelscited by 599
  16. 2023T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representationscited by 588
  17. 2023MotionGPT: Human Motion as a Foreign Languagecited by 527
  18. 2021Action-Conditioned 3D Human Motion Synthesis with Transformer VAEcited by 501
  19. 2022TEMOS: Generating diverse human motions from textual descriptionscited by 492
  20. 2021Diffusion Autoencoders: Toward a Meaningful and Decodable Representationcited by 449
  21. 2020Action2Motion: Conditioned Generation of 3D Human Motionscited by 441
  22. 2023Voicebox: Text-Guided Multilingual Universal Speech Generation at Scalecited by 379
  23. 2022TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Textscited by 359
  24. 2016The KIT Motion-Language Datasetcited by 338
  25. 2023Flow Matching on General Geometriescited by 265
  26. 2022Generating Holistic 3D Human Motion from Speechcited by 180
  27. 2020A Spatio-temporal Transformer for 3D Human Motion Predictioncited by 133
  28. 2019Generating 3D People in Scenes without Peoplecited by 127
  29. 2020We are More than Our Joints: Predicting how 3D Bodies Movecited by 115
  30. 2022Action Matching: Learning Stochastic Dynamics from Samplescited by 98
  31. 2023Human Motion Generation: A Surveycited by 96
  32. 2022Implicit Neural Representations for Variable Length Human Motion Generationcited by 61
  33. 2021Single-Shot Motion Completion with Transformercited by 59
  34. 2022MoDi: Unconditional Motion Synthesis from Diverse Datacited by 59
  35. 2022Future Transformer for Long-term Action Anticipationcited by 58
  36. 2022Fast Point Cloud Generation with Straight Flowscited by 56
  37. 2022Efficient Video Prediction via Sparsely Conditioned Flow Matchingcited by 55
  38. 2023Improved Techniques for Maximum Likelihood Estimation for Diffusion ODEscited by 54

50 most cited of 52 All 52 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 12; 2025: 11; 2026: 15.

38 papers.

Sort:

By area:

  1. 2024Rethinking Diffusion for Text-Driven Human Motion Generation: Redundant Representations, Evaluation, and Masked Autoregressioncited by 85
  2. 2024ZigMa: A DiT-style Zigzag Mamba Diffusion Modelcited by 84
  3. 2024DepthFM: Fast Monocular Depth Estimation with Flow Matchingcited by 76
  4. 2024Large Motion Model for Unified Multi-Modal Motion Generationcited by 65
  5. 2024Diffusion Models and Representation Learning: A Surveycited by 54
  6. 2024AdaFlow: Imitation Learning with Variance-Adaptive Flow-Based Policiescited by 50
  7. 2024Flow matching achieves almost minimax optimal convergencecited by 29
  8. 2025Absolute Coordinates Make Motion Generation Easycited by 29
  9. 2024FlowTS: Time Series Generation via Rectified Flowcited by 22
  10. 2024Fast and Robust Visuomotor Riemannian Flow Matching Policycited by 18
  11. 2025From Language to Locomotion: Retargeting-free Humanoid Control via Motion Latent Guidancecited by 18
  12. 2025Carr'e du champ flow matching: better quality-generalisation tradeoff in generative modelscited by 14
26 more
  1. 2024DiMSUM: Diffusion Mamba -- A Scalable and Unified Spatial-Frequency Method for Image Generationcited by 11
  2. 2024Learning Generalizable Human Motion Generator with Reinforcement Learningcited by 7
  3. 2025ARFlow: Human Action-Reaction Flow Matching with Physical Guidancecited by 7
  4. 2026Faster Inference of Flow-Based Generative Models via Improved Data-Noise Couplingcited by 7
  5. 2025Unified Multi-Modal Interactive & Reactive 3D Motion Generation via Rectified Flowcited by 6
  6. 2024Fake it to make it: Using synthetic data to remedy the data shortage in joint multimodal speech-and-gesture synthesiscited by 5
  7. 2026ProjFlow: Projection Sampling with Flow Matching for Zero-Shot Exact Spatial Motion Controlcited by 5
  8. 2025FlowMotion: Target-Predictive Conditional Flow Matching for Jitter-Reduced Text-Driven Human Motion Generationcited by 4
  9. 2026SemConFlow: Semantic Grounding of Holistic Co-Speech Gesture Generation with Contrastive Flow-Matchingcited by 4
  10. 2026MotionHiFlow: Text-to-motion via hierarchical flow matchingcited by 4
  11. 2025Learning by Neighbor-Aware Semantics, Deciding by Open-form Flows: Towards Robust Zero-Shot Skeleton Action Recognitioncited by 3
  12. 2026PRISM: Streaming Human Motion Generation with Per-Joint Latent Decompositioncited by 3
  13. 2025PlanMoGPT: Flow-Enhanced Progressive Planning for Text to Motion Synthesiscited by 2
  14. 2025MoReFlow: Motion Retargeting Learning through Unsupervised Flow Matchingcited by 2
  15. 2025Towards Stable and Structured Time Series Generation with Perturbation-Aware Flow Matchingcited by 2
  16. 2026From Diffusion to Flow: Efficient Motion Generation in MotionGPT3cited by 1
  17. 2026MoSAT: Human Motion Generation from Spatial Audio and Textual Descriptioncited by 1
  18. 2025Real-Time Person Image Synthesis Using a Flow Matching Modelcited by 0
  19. 2026InterEdit: Navigating Text-Guided 3D Dyadic Human Motion Editingcited by 0
  20. 2026Unified Number-Free Text-to-Motion Generation Via Flow Matchingcited by 0
  21. 2026Before the Body Moves: Learning Anticipatory Joint Intent for Language-Conditioned Humanoid Controlcited by 0
  22. 2026SubtleTalk: Generating Controllable Weakly-correlated Facial Dynamics for 3D Talking Heads via Residual Flow Matchingcited by 0
  23. 2026Learning to Beat: Phenotype-Guided Latent Flow with Regional Motion Priors for Biventricular Motion Synthesiscited by 0
  24. 2026Skeletons in Flow: Graph Structured Flow Matching for Human Motion Predictioncited by 0
  25. 2026TAME:Topology-Aware Text-Driven Motion Editing across Heterogeneous Humanoid Skeletonscited by 0
  26. 2026MFlowHOI: Whole-Body Human-Object Interaction Generation via Part-Aware MeanFlowcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Towards motion from video diffusion models
  2. 2025HY-Motion 1.0: Scaling Flow Matching Models for Text-To-Motion Generation
  3. 2022FLAME: Free-form Language-based Motion Synthesis & Editing
  4. 2022Unifying Human Motion Synthesis and Style Transfer with Denoising Diffusion Probabilistic Models
  5. 2026UniMoFlow: Grounding Instruction-Driven 3D Human Motion Editing in Generation
  6. 2024Human Motion Synthesis_ A Diffusion Approach for Motion Stitching and In-Betweening
  7. 2022Pretrained Diffusion Models for Unified Human Motion Synthesis
  8. 2023Synthesizing Long-Term Human Motions with Diffusion Models via Coherent Sampling