mlsanityData to 14 Oct 2026

FlowMotion: Target-Predictive Conditional Flow Matching for Jitter-Reduced Text-Driven Human Motion Generation

arXiv 2504.01338 ↗First posted 2 Apr 2025cs.GR cs.LGcited by 4

On the map: Diffusion models → Video generation

Abstract (arXiv)

Achieving high-fidelity and temporally smooth 3D human motion generation remains a challenge, particularly within resource-constrained environments. We introduce FlowMotion, a novel method leveraging Conditional Flow Matching (CFM). FlowMotion incorporates a training objective within CFM that focuses on more accurately predicting target motion in 3D human motion generation, resulting in enhanced generation fidelity and temporal smoothness while maintaining the fast synthesis times characteristic of flow-matching-based methods. FlowMotion achieves state-of-the-art jitter performance, achieving the best jitter in the KIT dataset and the second-best jitter in the HumanML3D dataset, and a competitive FID value in both datasets. This combination provides robust and natural motion sequences, offering a promising equilibrium between generation quality and temporal naturalness.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Placed in Video generation, one of 14 directions in Diffusion models. Builds on 47 of its 64 references that are in the map. First posted on arXiv 2 Apr 2025.

Builds on

47 of 64 references.

Closest ancestors · 9

Same direction, newest first

  1. 2024Flexible Motion In-betweening with Diffusion Models17 May
  2. 2024MotionLCM: Real-time Controllable Motion Generation via Latent Consistency Model30 Apr
  3. 2024Generating Human Interaction Motions in Scenes with Text Control16 Apr
  4. 2023Motion Flow Matching for Human Motion Synthesis and Editing14 Dec
  5. 2023EMDM: Efficient Motion Diffusion Model for Fast and High-Quality Motion Generation4 Dec
  6. 2023Dysen-VDM: Empowering Dynamics-aware Text-to-Video Diffusion with LLMs26 Aug
  7. 2023Guided Motion Diffusion for Controllable Human Motion Synthesis21 May
  8. 2022Executing your Commands via Motion Diffusion in Latent Space8 Dec
  9. 2022FLAME: Free-form Language-based Motion Synthesis & Editing1 Sep

Other references · 38

  1. 2017Attention Is All You Needcited by 60,361
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  3. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  4. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  5. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,585
  6. 2022Flow Matching for Generative Modelingcited by 5,702
  7. 2014Sequence to Sequence Learning with Neural Networkscited by 2,986
  8. 2019AMASS: Archive of Motion Capture as Surface Shapescited by 1,236
  9. 2023T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representationscited by 588
  10. 2023MotionGPT: Human Motion as a Foreign Languagecited by 527
  11. 2021Action-Conditioned 3D Human Motion Synthesis with Transformer VAEcited by 501
  12. 2022TEMOS: Generating diverse human motions from textual descriptionscited by 492
26 more
  1. 2020Action2Motion: Conditioned Generation of 3D Human Motionscited by 441
  2. 2022TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Textscited by 359
  3. 2016The KIT Motion-Language Datasetcited by 338
  4. 2024Flow Matching Guide and Codecited by 301
  5. 2023Diffusion-based Generation, Optimization, and Planning in 3D Scenescited by 239
  6. 2022MoFusion: A Framework for Denoising-Diffusion-based Motion Synthesiscited by 218
  7. 2021Stochastic Scene-Aware Motion Predictioncited by 203
  8. 2017HP-GAN: Probabilistic 3D human motion prediction via GANcited by 176
  9. 2022TEACH: Temporal Action Composition for 3D Humanscited by 176
  10. 2023Noise2Music: Text-conditioned Music Generation with Diffusion Modelscited by 173
  11. 2020Populating 3D Scenes by Learning Human-Scene Interactioncited by 164
  12. 2024Expressive Whole-Body Control for Humanoid Robotscited by 139
  13. 2019Generating 3D People in Scenes without Peoplecited by 127
  14. 2018Human Motion Prediction via Spatio-Temporal Inpaintingcited by 114
  15. 2023Avatars Grow Legs: Generating Smooth Human Motion from Sparse Tracking Inputs with Diffusion Modelcited by 107
  16. 2017Text2Action: Generative Adversarial Synthesis from Language to Actioncited by 106
  17. 2021Text2Gestures: A Transformer-Based Network for Generating Emotive Body Gestures for Virtual Agentscited by 106
  18. 2024Seamless Human Motion Composition with Blended Positional Encodingscited by 80
  19. 2021Single-Shot Motion Completion with Transformercited by 59
  20. 2024Autonomous Character-Scene Interaction Synthesis from Text Instructioncited by 56
  21. 2024Flow Generator Matchingcited by 26
  22. 2021Generative Adversarial Graph Convolutional Networks for Human Action Synthesiscited by 23
  23. 2024Harmon: Whole-Body Motion Generation of Humanoid Robots from Language Descriptionscited by 23
  24. 2024Real-Time Simulated Avatar from Head-Mounted Sensorscited by 17
  25. 2023ERNIE-Music: Text-to-Waveform Music Generation with Diffusion Modelscited by 15
  26. 2024Human Motion Synthesis_ A Diffusion Approach for Motion Stitching and In-Betweeningcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 3.

4 papers.

  1. 2026ProjFlow: Projection Sampling with Flow Matching for Zero-Shot Exact Spatial Motion Controlcited by 5
  2. 2025MoReFlow: Motion Retargeting Learning through Unsupervised Flow Matchingcited by 2
  3. 2026A Unified Conditional Flow for Motion Generation, Editing, and Intra-Structural Retargetingcited by 1
  4. 2026MFlowHOI: Whole-Body Human-Object Interaction Generation via Part-Aware MeanFlowcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025HY-Motion 1.0: Scaling Flow Matching Models for Text-To-Motion Generation
  2. 2026MotionHiFlow: Text-to-motion via hierarchical flow matching
  3. 2026From Diffusion to Flow: Efficient Motion Generation in MotionGPT3
  4. 2026PRISM: Streaming Human Motion Generation with Per-Joint Latent Decomposition
  5. 2025Unified Multi-Modal Interactive & Reactive 3D Motion Generation via Rectified Flow
  6. 2026MotionSpaceFlow: Representation-Aware Flow Matching in Direct Motion Space
  7. 2026World2Motion: Turning Video World Models into 3D Human Motion Generators
  8. 2024DisCoRD: Discrete Tokens to Continuous Motion via Rectified Flow Decoding