mlsanityData to 14 Oct 2026

Shape My Moves: Text-Driven Shape-Aware Synthesis of Human Motions

arXiv 2504.03639 ↗First posted 4 Apr 2025cs.CVcited by 11

Not on the map. Why?

Abstract (arXiv)

We explore how body shapes influence human motion synthesis, an aspect often overlooked in existing text-to-motion generation methods due to the ease of learning a homogenized, canonical body shape. However, this homogenization can distort the natural correlations between different body shapes and their motion dynamics. Our method addresses this gap by generating body-shape-aware human motions from natural language prompts. We utilize a finite scalar quantization-based variational autoencoder (FSQ-VAE) to quantize motion into discrete tokens and then leverage continuous body shape information to de-quantize these tokens back into continuous, detailed motion. Additionally, we harness the capabilities of a pretrained language model to predict both continuous shape parameters and motion tokens, facilitating the synthesis of text-aligned motions and decoding them into shape-aware motions. We evaluate our method quantitatively and qualitatively, and also conduct a comprehensive perceptual study to demonstrate its efficacy in generating shape-aware motions.

Key facts. Cited by 11 papers in the map (data through 14 Oct 2026). Builds on 71 of its 111 references that are in the map. First posted on arXiv 4 Apr 2025.

Builds on

71 of 111 references.

References · 71

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  3. 2017Neural Discrete Representation Learningcited by 4,712
  4. 2015High-Dimensional Continuous Control Using Generalized Advantage Estimationcited by 2,026
  5. 2019Expressive Body Capture: 3D Hands, Face, and Body from a Single Imagecited by 1,612
  6. 2019AMASS: Archive of Motion Capture as Surface Shapescited by 1,236
  7. 2022Human Motion Diffusion Modelcited by 1,080
  8. 2021Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learningcited by 998
  9. 2022MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Modelcited by 780
  10. 2023LISA: Reasoning Segmentation via Large Language Modelcited by 776
  11. 2016Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Imagecited by 695
  12. 2023T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representationscited by 588
38 more
  1. 2022Executing your Commands via Motion Diffusion in Latent Spacecited by 575
  2. 2023MotionGPT: Human Motion as a Foreign Languagecited by 527
  3. 2021Action-Conditioned 3D Human Motion Synthesis with Transformer VAEcited by 501
  4. 2022TEMOS: Generating diverse human motions from textual descriptionscited by 492
  5. 2021AI Choreographer: Music Conditioned 3D Dance Generation with AIST++cited by 485
  6. 2020Action2Motion: Conditioned Generation of 3D Human Motionscited by 441
  7. 2023Finite Scalar Quantization: VQ-VAE Made Simplecited by 440
  8. 2022MotionCLIP: Exposing Human Motion Generation to CLIP Spacecited by 408
  9. 2023MoMask: Generative Masked Modeling of 3D Human Motionscited by 400
  10. 2022PhysDiff: Physics-Guided Human Motion Diffusion Modelcited by 368
  11. 2022TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Textscited by 359
  12. 2023Human Motion Diffusion as a Generative Priorcited by 357
  13. 2016The KIT Motion-Language Datasetcited by 338
  14. 2022Analytic-DPM: an Analytic Estimate of the Optimal Reverse Variance in Diffusion Probabilistic Modelscited by 334
  15. 2021HuMoR: 3D Human Motion Model for Robust Pose Estimationcited by 324
  16. 2022EDGE: Editable Dance Generation From Musiccited by 287
  17. 2019Language2Pose: Natural Language Grounded Pose Forecastingcited by 257
  18. 2022MoFusion: A Framework for Denoising-Diffusion-based Motion Synthesiscited by 218
  19. 2019Learning Individual Styles of Conversational Gesturecited by 191
  20. 2020DLow: Diversifying Latent Flows for Diverse Human Motion Predictioncited by 185
  21. 2021Synthesis of Compositional Animations from Textual Descriptionscited by 178
  22. 2017HP-GAN: Probabilistic 3D human motion prediction via GANcited by 176
  23. 2022TEACH: Temporal Action Composition for 3D Humanscited by 176
  24. 2022Physical Inertial Poser (PIP): Physics-aware Real-time Human Motion Tracking from Sparse Inertial Sensorscited by 146
  25. 2024Scaling Up Dynamic Human-Scene Interaction Modelingcited by 137
  26. 2020Skeleton-Aware Networks for Deep Motion Retargetingcited by 124
  27. 2022IMos: Intent-Driven Full-Body Motion Synthesis for Human-Object Interactionscited by 124
  28. 2021SimPoE: Simulated Character Control for 3D Human Pose Estimationcited by 114
  29. 2024Motion Mamba: Efficient and Long Sequence Motion Generationcited by 112
  30. 2017Text2Action: Generative Adversarial Synthesis from Language to Actioncited by 106
  31. 2021Text2Gestures: A Transformer-Based Network for Generating Emotive Body Gestures for Virtual Agentscited by 106
  32. 20233D Human Pose Estimation via Intuitive Physicscited by 103
  33. 2017Deep representation learning for human motion prediction and classificationcited by 98
  34. 2019Structured Prediction Helps 3D Human Motion Modellingcited by 96
  35. 2018A Neural Temporal Model for Human Motion Predictioncited by 87
  36. 2023ChatPose: Chatting about 3D Human Posecited by 72
  37. 2021Neural Monocular 3D Human Motion Capture with Physical Awarenesscited by 71
  38. 2022NeMF: Neural Motion Fields for Kinematic Animationcited by 68

50 most cited of 71 All 71 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 4; 2026: 7.

11 papers.

  1. 2025Absolute Coordinates Make Motion Generation Easycited by 29
  2. 2025X-MoGen: Unified Motion Generation across Humans and Animalscited by 4
  3. 2026Beyond Global Alignment: Fine-Grained Motion-Language Retrieval via Pyramidal Shapley-Taylor Learningcited by 4
  4. 2026Next-Scale Autoregressive Models for Text-to-Motion Generationcited by 4
  5. 2025Topology-Agnostic Animal Motion Generation from Text Promptcited by 2
  6. 2026U-Mind: A Unified Framework for Real-Time Multimodal Interaction with Audiovisual Generationcited by 2
  7. 2026ReactMotion: Generating Reactive Listener Motions from Speaker Utterancecited by 1
  8. 2026IAM: Identity-Aware Human Motion and Shape Joint Generationcited by 1
  9. 2025FashionPose: Unified Text-Driven Fashion Synthesis with Joint Geometric and Photometric Controlcited by 0
  10. 2026Odoriko: A Shape-Aware Multimodal Diffusion Framework for Human Motioncited by 0
  11. 2026MorphoStyle: Motion Style Transfer with Morphology Controlcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024MotionGPT-2: A General-Purpose Motion-Language Model for Motion Generation and Understanding
  2. 2023A Unified Framework for Multimodal, Multi-Part Human Motion Synthesis
  3. 2022Generating Holistic 3D Human Motion from Speech
  4. 2024LEAD: Latent Realignment for Human Motion Diffusion
  5. 2026ScaleMoGen: Autoregressive Next-Scale Prediction for Human Motion Generation
  6. 2024GUESS:GradUally Enriching SyntheSis for Text-Driven Human Motion Generation
  7. 2026FrankenMotion: Part-level Human Motion Generation and Composition
  8. 2024T2M-X: Learning Expressive Text-to-Motion Generation from Partially Annotated Data