awesome-text-to-motion

Text-driven human motion generation surveys, datasets and models, focusing on single-person scenarios without human-object/scene interaction. Please refer to the project page for a better browsing experience with interactive visualizations and statistical charts.

Contribution Guide (Click to expand)

---

We welcome contributions to make this repository more comprehensive and up-to-date!

How to Contribute

1. Fork this repository to your GitHub account
2. Create a new branch for your contribution
3. Add your papers following the guidelines below
4. Submit a Pull Request with a clear description of your changes

Adding Papers

For Papers with arXiv IDs:

• File: data/arxiv.csv
• Format: Add a new row with the following columns:
  • arxiv_id: The arXiv ID (e.g., "2507.05419")
  • survey: "1" if it's a survey paper, "0" otherwise
  • survey_abbr: Abbreviation for survey papers (e.g., "Survey2507")
  • model: "1" if it's a model paper, "0" otherwise
  • model_abbr: Abbreviation for model papers (e.g., "MotionGen")
  • dataset: "1" if it's a dataset paper, "0" otherwise
  • dataset_abbr: Abbreviation for dataset papers (e.g., "MotionX")
  • submission: Conference/journal name (e.g., "CVPR")
  • submission_year: Year of submission (e.g., "2025")
  • page: Project page URL (if available)
  • repo: GitHub repository URL (if available)
  • backbone_tags: Comma-separated backbone tags (e.g., "Transformer, Diffusion")
  • approach_tags: Comma-separated approach tags (e.g., "Physical, Editing")

For Papers without arXiv IDs:

• File: data/without-arxiv.json
• Format: Add a new JSON object with the following structure:

{
    "arxiv_id": "random-key-for-your-interest",
    "title": "Paper Title",
    "abstract": "Paper abstract...",
    "authors": ["Author 1", "Author 2"],
    "year": 2025,
    "month": 7,
    "url": "https://paper-url.com",
    "survey": false,
    "survey_abbr": "",
    "model": true,
    "model_abbr": "ModelName",
    "dataset": false,
    "dataset_abbr": "",
    "submission": "Conference",
    "submission_year": "2025",
    "page": "https://project-page.com",
    "repo": "https://github.com/user_name/repo",
    "backbone_tags": "Transformer, Diffusion",
    "approach_tags": "Physical, Editing"
}

Thank you for contributing to the awesome-text-to-motion collection! 🚀

---

Contents

• Surveys
• Datasets
• Models

Surveys

• "Motion Generation: A Survey of Generative Approaches and Benchmarks". arXiv(2025) [URL]

• "Multimodal Generative AI with Autoregressive LLMs for Human Motion Understanding and Generation: A Way Forward". arXiv(2025) [URL]

• "Text-driven Motion Generation: Overview, Challenges and Directions". arXiv(2025) [URL]

• "Human Motion Generation: A Survey". TPAMI(2023) [URL]

Datasets

• UniMo4D: "X-MoGen: Unified Motion Generation across Humans and Animals". arXiv(2025) [URL]

• FineMotion: "FineMotion: A Dataset and Benchmark with both Spatial and Temporal Annotation for Fine-grained Motion Generation and Editing". arXiv(2025) [URL] [Code]

• SnapMoGen: "SnapMoGen: Human Motion Generation from Expressive Texts". arXiv(2025) [URL] [Project Page] [Code]

• MotionMillion: "Go to Zero: Towards Zero-shot Motion Generation with Million-scale Data". ICCV(2025) [URL] [Project Page] [Code]

• HumanAttr: "Generating Attribute-Aware Human Motions from Textual Prompt". arXiv(2025) [URL]

• GBC-100K: "From Motion to Behavior: Hierarchical Modeling of Humanoid Generative Behavior Control". arXiv(2025) [URL]

• STANCE: "Dynamic Motion Blending for Versatile Motion Editing". CVPR(2025) [URL] [Project Page] [Code]

• PerMo: "PersonaBooth: Personalized Text-to-Motion Generation". CVPR(2025) [URL] [Project Page] [Code]

• TMD: "Motion Anything: Any to Motion Generation". arXiv(2025) [URL] [Project Page]

• Motion-X++: "Motion-X++: A Large-Scale Multimodal 3D Whole-body Human Motion Dataset". arXiv(2025) [URL]

• MotionFix: "MotionFix: Text-Driven 3D Human Motion Editing". SIGGRAPH Asia(2024) [URL] [Project Page] [Code]

• HumanML3D-Extend: "Infinite Motion: Extended Motion Generation via Long Text Instructions". arXiv(2024) [URL] [Project Page]

• MotionPercept: "Aligning Human Motion Generation with Human Perceptions". ICLR(2025) [URL] [Project Page] [Code]

• PaM: "MoDiPO: text-to-motion alignment via AI-feedback-driven Direct Preference Optimization". arXiv(2024) [URL]

• HumanML3D++: "You Think, You ACT: The New Task of Arbitrary Text to Motion Generation". ICCV(2025) [URL]

• MotionVerse: "Large Motion Model for Unified Multi-Modal Motion Generation". arXiv(2024) [URL] [Project Page] [Code]

• RICH-CAT: "Contact-aware Human Motion Generation from Textual Descriptions". arXiv(2024) [URL] [Project Page]

• FineHumanML3D: "Motion Generation from Fine-grained Textual Descriptions". LREC-COLING(2024) [URL] [Code]

• BlindWays: "Text to Blind Motion". NeurIPS(2024) [URL] [Project Page]

• LaViMo: "Text Motion Translator: A Bi-Directional Model for Enhanced 3D Human Motion Generation from Open-Vocabulary Descriptions". ECCV(2024) [URL]

• Inter-MT2: "A Unified Framework for Motion Reasoning and Generation in Human Interaction". ICCV(2025) [URL] [Project Page]

• MotionLib: "Scaling Large Motion Models with Million-Level Human Motions". ICML(2025) [URL] [Project Page] [Code]

• HumanML3D-synthesis: "CLaM: An Open-Source Library for Performance Evaluation of Text-driven Human Motion Generation". MM(24) [URL] [Code]

• Limb-ET2M: "Towards Emotion-enriched Text-to-Motion Generation via LLM-guided Limb-level Emotion Manipulating ". MM(2024) [URL] [Code]

• Motion-X: "Motion-X: A Large-scale 3D Expressive Whole-body Human Motion Dataset". NeurIPS(2023) [URL] [Project Page] [Code]

• HumanLong3D: "AMD: Autoregressive Motion Diffusion". AAAI(2024) [URL] [Code]

• HuMMan-MoGen: "FineMoGen: Fine-Grained Spatio-Temporal Motion Generation and Editing". NeurIPS(2023) [URL] [Project Page] [Code]

• HumanML3D: "Generating Diverse and Natural 3D Human Motions from Text". CVPR(2022) [URL] [Project Page] [Code]

• KIT: "The KIT Motion-Language Dataset". Big Data(2016) [URL] [Project Page]

Models

• X-MoGen: "X-MoGen: Unified Motion Generation across Humans and Animals". arXiv(2025) [URL]

• ReMoMask: "ReMoMask: Retrieval-Augmented Masked Motion Generation". arXiv(2025) [URL] [Project Page] [Code]

• SASI: "Semantically Consistent Text-to-Motion with Unsupervised Styles". SIGGRAPH(2025) [URL] [Project Page]

• MoMask++: "SnapMoGen: Human Motion Generation from Expressive Texts". arXiv(2025) [URL] [Project Page] [Code]

• GotoZero: "Go to Zero: Towards Zero-shot Motion Generation with Million-scale Data". ICCV(2025) [URL] [Project Page] [Code]

• MOST: "MOST: Motion Diffusion Model for Rare Text via Temporal Clip Banzhaf Interaction". arXiv(2025) [URL]

• MotionGPT3: "MotionGPT3: Human Motion as a Second Modality". arXiv(2025) [URL] [Project Page] [Code]

• AttrMoGen: "Generating Attribute-Aware Human Motions from Textual Prompt". arXiv(2025) [URL]

• Motion-R1: "Motion-R1: Chain-of-Thought Reasoning and Reinforcement Learning for Human Motion Generation". arXiv(2025) [URL] [Project Page] [Code]

• MOGO: "MOGO: Residual Quantized Hierarchical Causal Transformer for High-Quality and Real-Time 3D Human Motion Generation". arXiv(2025) [URL]

• ANT: "ANT: Adaptive Neural Temporal-Aware Text-to-Motion Model". arXiv(2025) [URL] [Code]

• PHYLOMAN: "From Motion to Behavior: Hierarchical Modeling of Humanoid Generative Behavior Control". arXiv(2025) [URL]

• ACMDM: "Absolute Coordinates Make Motion Generation Easy". arXiv(2025) [URL] [Project Page] [Code]

• MoMADiff: "Towards Robust and Controllable Text-to-Motion via Masked Autoregressive Diffusion". MM(2025) [URL] [Code]

• ReAlign: "ReAlign: Bilingual Text-to-Motion Generation via Step-Aware Reward-Guided Alignment". arXiv(2025) [URL] [Project Page]

• GENMO: "GENMO: A GENeralist Model for Human MOtion". arXiv(2025) [URL] [Project Page]

• DSDFM: "Deterministic-to-Stochastic Diverse Latent Feature Mapping for Human Motion Synthesis". CVPR(2025) [URL]

• UniPhys: "UniPhys: Unified Planner and Controller with Diffusion for Flexible Physics-Based Character Control". ICCV(2025) [URL] [Project Page]

• Shape-Move: "Shape My Moves: Text-Driven Shape-Aware Synthesis of Human Motions". CVPR(2025) [URL] [Project Page] [Code]

• MG-MotionLLM: "MG-MotionLLM: A Unified Framework for Motion Comprehension and Generation across Multiple Granularities". CVPR(2025) [URL] [Code]

• FlowMotion: "FlowMotion: Target-Predictive Conditional Flow Matching for Jitter-Reduced Text-Driven Human Motion Generation". arXiv(2025) [URL]

• MixerMDM: "MixerMDM: Learnable Composition of Human Motion Diffusion Models". CVPR(2025) [URL] [Project Page] [Code]

• ReMoGPT: "ReMoGPT: Part-Level Retrieval-Augmented Motion-Language Models". AAAI(2025) [URL]

• UniTMGE: "UniTMGE: Uniform Text-Motion Generation and Editing Model via Diffusion". WACV(2025) [URL]

• MotionReFit: "Dynamic Motion Blending for Versatile Motion Editing". CVPR(2025) [URL] [Project Page] [Code]

• LoRA-MDM: "Dance Like a Chicken: Low-Rank Stylization for Human Motion Diffusion". arXiv(2025) [URL] [Project Page] [Code]

• HMU: "Human Motion Unlearning". arXiv(2025) [URL] [Project Page] [Code]

• SimMotionEdit: "SimMotionEdit: Text-Based Human Motion Editing with Motion Similarity Prediction". CVPR(2025) [URL] [Project Page] [Code]

• MotionStreamer: "MotionStreamer: Streaming Motion Generation via Diffusion-based Autoregressive Model in Causal Latent Space". ICCV(2025) [URL] [Project Page] [Code]

• GenM3: "GenM$^3$: Generative Pretrained Multi-path Motion Model for Text Conditional Human Motion Generation". arXiv(2025) [URL]

• Kinesis: "Reinforcement learning-based motion imitation for physiologically plausible musculoskeletal motor control". arXiv(2025) [URL] [Code]

• sMDM: "Less is More: Improving Motion Diffusion Models with Sparse Keyframes". arXiv(2025) [URL]

• SALAD: "SALAD: Skeleton-aware Latent Diffusion for Text-driven Motion Generation and Editing". CVPR(2025) [URL] [Project Page] [Code]

• PMG: "Progressive Human Motion Generation Based on Text and Few Motion Frames". TCSVT(2025) [URL] [Code]

• PersonaBooth: "PersonaBooth: Personalized Text-to-Motion Generation". CVPR(2025) [URL] [Project Page] [Code]

• MotionAnything: "Motion Anything: Any to Motion Generation". arXiv(2025) [URL] [Project Page]

• BioVAE: "Biomechanics-Guided Residual Approach to Generalizable Human Motion Generation and Estimation". arXiv(2025) [URL]

• MoMug: "Unlocking Pretrained LLMs for Motion-Related Multimodal Generation: A Fine-Tuning Approach to Unify Diffusion and Next-Token Prediction". arXiv(2025) [URL]

• Fg-T2M++: "Fg-T2M++: LLMs-Augmented Fine-Grained Text Driven Human Motion Generation". IJCV(2025) [URL]

• MotionLab: "MotionLab: Unified Human Motion Generation and Editing via the Motion-Condition-Motion Paradigm". ICCV(2025) [URL] [Project Page] [Code]

• CASIM: "CASIM: Composite Aware Semantic Injection for Text to Motion Generation". arXiv(2025) [URL] [Project Page] [Code]

• SPORT: "SPORT: From Zero-shot Prompts to Real-time Motion Generation". TVCG(2025) [URL]

• MotionPCM: "MotionPCM: Real-Time Motion Synthesis with Phased Consistency Model". arXiv(2025) [URL]

• Free-T2M: "Free-T2M: Frequency Enhanced Text-to-Motion Diffusion Model With Consistency Loss". arXiv(2025) [URL]

• FlexMotion: "FlexMotion: Lightweight, Physics-Aware, and Controllable Human Motion Generation". arXiv(2025) [URL] [Project Page]

• PackDiT: "PackDiT: Joint Human Motion and Text Generation via Mutual Prompting". arXiv(2025) [URL]

• MMDM: "Text-driven Human Motion Generation with Motion Masked Diffusion Model". arXiv(2024) [URL]

• EgoLM: "EgoLM: Multi-Modal Language Model of Egocentric Motions". CVPR(2025) [URL] [Project Page]

• MoGenTS: "MoGenTS: Motion Generation based on Spatial-Temporal Joint Modeling". NeurIPS(2024) [URL] [Project Page] [Code]

• UniMotion: "Unimotion: Unifying 3D Human Motion Synthesis and Understanding". 3DV(2025) [URL] [Project Page] [Code]

• MaskedMimic: "MaskedMimic: Unified Physics-Based Character Control Through Masked Motion Inpainting". SIGGRAPH Asia(2024) [URL] [Project Page] [Code]

• T2M-X: "T2M-X: Learning Expressive Text-to-Motion Generation from Partially Annotated Data". arXiv(2024) [URL]

• MoRAG: "MoRAG -- Multi-Fusion Retrieval Augmented Generation for Human Motion". WACV(2025) [URL] [Project Page] [Code]

• BAD: "BAD: Bidirectional Auto-regressive Diffusion for Text-to-Motion Generation". arXiv(2024) [URL] [Project Page] [Code]

• LaMoG: "Lagrangian Motion Fields for Long-term Motion Generation". arXiv(2024) [URL] [Project Page]

• TextIM: "TextIM: Part-aware Interactive Motion Synthesis from Text". EUROGRAPHICS(2025) [URL]

• TMED: "MotionFix: Text-Driven 3D Human Motion Editing". SIGGRAPH Asia(2024) [URL] [Project Page] [Code]

• ALERT-Motion: "Autonomous LLM-Enhanced Adversarial Attack for Text-to-Motion". AAAI(2025) [URL]

• MotionCraft: "MotionCraft: Crafting Whole-Body Motion with Plug-and-Play Multimodal Controls". AAAI(2025) [URL] [Project Page] [Code]

• M2D2M: "M2D2M: Multi-Motion Generation from Text with Discrete Diffusion Models". ECCV(2024) [URL]

• SMooDi: "SMooDi: Stylized Motion Diffusion Model". ECCV(2024) [URL] [Project Page] [Code]

• GuidedMotion: "Local Action-Guided Motion Diffusion Model for Text-to-Motion Generation". arXiv(2024) [URL] [Project Page]

• SuperPADL: "SuperPADL: Scaling Language-Directed Physics-Based Control with Progressive Supervised Distillation". arXiv(2024) [URL]

• InfiniMotion: "InfiniMotion: Mamba Boosts Memory in Transformer for Arbitrary Long Motion Generation". arXiv(2024) [URL]

• InfiniteMotion: "Infinite Motion: Extended Motion Generation via Long Text Instructions". arXiv(2024) [URL] [Project Page]

• MotionGPT: "MotionGPT: Human Motion Synthesis with Improved Diversity and Realism via GPT-3 Prompting". WACV(2024) [URL] [Code]

• MoLA: "MoLA: Motion Generation and Editing with Latent Diffusion Enhanced by Adversarial Training". CVPR Workshop(2025) [URL] [Project Page] [Code]

• T2LM: "T2LM: Long-Term 3D Human Motion Generation from Multiple Sentences". CVPR Workshop(2024) [URL]

• ProgMoGen: "Programmable Motion Generation for Open-Set Motion Control Tasks". CVPR(2024) [URL] [Project Page] [Code]

• Motion-Agent: "Motion-Agent: A Conversational Framework for Human Motion Generation with LLMs". ICLR(2025) [URL] [Project Page] [Code]

• TMR++: "A Cross-Dataset Study for Text-based 3D Human Motion Retrieval". CVPR Workshop(2024) [URL] [Project Page] [Code]

• M3GPT: "M$^3$GPT: An Advanced Multimodal, Multitask Framework for Motion Comprehension and Generation". NeurIPS(2024) [URL] [Project Page] [Code]

• InstructMotion: "Learning Generalizable Human Motion Generator with Reinforcement Learning". arXiv(2024) [URL]

• SMD: "Shape Conditioned Human Motion Generation with Diffusion Model". arXiv(2024) [URL]

• StableMoFusion: "StableMoFusion: Towards Robust and Efficient Diffusion-based Motion Generation Framework". MM(2024) [URL] [Project Page] [Code]

• MotionPatches: "Exploring Vision Transformers for 3D Human Motion-Language Models with Motion Patches". CVPR(2024) [URL] [Project Page] [Code]

• MoDiPO: "MoDiPO: text-to-motion alignment via AI-feedback-driven Direct Preference Optimization". arXiv(2024) [URL]

• LGTM: "LGTM: Local-to-Global Text-Driven Human Motion Diffusion Model". SIGGRAPH(2024) [URL] [Code]

• MLCT: "Efficient Text-driven Motion Generation via Latent Consistency Training". arXiv(2024) [URL]

• SATO: "SATO: Stable Text-to-Motion Framework". MM(2024) [URL] [Project Page] [Code]

• MotionLCM: "MotionLCM: Real-time Controllable Motion Generation via Latent Consistency Model". ECCV(2024) [URL] [Project Page] [Code]

• TAAT: "You Think, You ACT: The New Task of Arbitrary Text to Motion Generation". ICCV(2025) [URL]

• MCM: "MCM: Multi-condition Motion Synthesis Framework". arXiv(2024) [URL]

• InstructMotion: "Exploring Text-to-Motion Generation with Human Preference". CVPR Workshop(2024) [URL] [Code]

• MotionChain: "MotionChain: Conversational Motion Controllers via Multimodal Prompts". arXiv(2024) [URL]

• LMM: "Large Motion Model for Unified Multi-Modal Motion Generation". arXiv(2024) [URL] [Project Page] [Code]

• BAMM: "BAMM: Bidirectional Autoregressive Motion Model". ECCV(2024) [URL] [Project Page] [Code]

• ParCo: "ParCo: Part-Coordinating Text-to-Motion Synthesis". ECCV(2024) [URL] [Code]

• CATMO: "Contact-aware Human Motion Generation from Textual Descriptions". arXiv(2024) [URL] [Project Page]

• CoMo: "CoMo: Controllable Motion Generation through Language Guided Pose Code Editing". ECCV(2024) [URL] [Project Page] [Code]

• AnySkill: "AnySkill: Learning Open-Vocabulary Physical Skill for Interactive Agents". CVPR(2024) [URL] [Project Page] [Code]

• MotionMamba: "Motion Mamba: Efficient and Long Sequence Motion Generation". ECCV(2024) [URL] [Project Page]

• MMoFusion: "MMoFusion: Multi-modal Co-Speech Motion Generation with Diffusion Model". arXiv(2024) [URL] [Project Page] [Code]

• FlowMDM: "Seamless Human Motion Composition with Blended Positional Encodings". CVPR(2024) [URL] [Project Page] [Code]

• LS-GAN: "LS-GAN: Human Motion Synthesis with Latent-space GANs". WACV(2025) [URL] [Code]

• EnergyMoGen: "EnergyMoGen: Compositional Human Motion Generation with Energy-Based Diffusion Model in Latent Space". CVPR(2025) [URL] [Project Page]

• ScaMo: "ScaMo: Exploring the Scaling Law in Autoregressive Motion Generation Model". CVPR(2025) [URL] [Project Page] [Code]

• Light-T2M: "Light-T2M: A Lightweight and Fast Model for Text-to-motion Generation". AAAI(2025) [URL] [Code]

• LoM: "The Language of Motion: Unifying Verbal and Non-verbal Language of 3D Human Motion". arXiv(2024) [URL] [Project Page] [Code]

• CoMA: "CoMA: Compositional Human Motion Generation with Multi-modal Agents". arXiv(2024) [URL] [Project Page] [Code]

• SoPo: "SoPo: Text-to-Motion Generation Using Semi-Online Preference Optimization". arXiv(2024) [URL] [Project Page] [Code]

• RMD: "RMD: A Simple Baseline for More General Human Motion Generation via Training-free Retrieval-Augmented Motion Diffuse". arXiv(2024) [URL]

• BiPO: "BiPO: Bidirectional Partial Occlusion Network for Text-to-Motion Synthesis". arXiv(2024) [URL]

• MoTE: "MoTe: Learning Motion-Text Diffusion Model for Multiple Generation Tasks". arXiv(2024) [URL]

• FTMoMamba: "FTMoMamba: Motion Generation with Frequency and Text State Space Models". arXiv(2024) [URL]

• VersatileMotion: "VersatileMotion: A Unified Framework for Motion Synthesis and Comprehension". arXiv(2024) [URL]

• MARDM: "Rethinking Diffusion for Text-Driven Human Motion Generation: Redundant Representations, Evaluation, and Masked Autoregression". CVPR(2025) [URL] [Project Page] [Code]

• Morph: "Morph: A Motion-free Physics Optimization Framework for Human Motion Generation". ICCV(2025) [URL]

• KMM: "KMM: Key Frame Mask Mamba for Extended Motion Generation". arXiv(2024) [URL] [Project Page]

• TMT: "Text Motion Translator: A Bi-Directional Model for Enhanced 3D Human Motion Generation from Open-Vocabulary Descriptions". ECCV(2024) [URL]

• M-Adaptor: "M-Adaptor: Text-driven Whole-body Human Motion Generation". CVPR Workshop(2025) [URL]

• MotionGPT-2: "MotionGPT-2: A General-Purpose Motion-Language Model for Motion Generation and Understanding". arXiv(2024) [URL]

• MotionCLR: "Pay Attention and Move Better: Harnessing Attention for Interactive Motion Generation and Training-free Editing". arXiv(2024) [URL] [Project Page]

• LEAD: "LEAD: Latent Realignment for Human Motion Diffusion". arXiv(2024) [URL]

• MaskControl: "MaskControl: Spatio-Temporal Control for Masked Motion Synthesis". ICCV(2025) [URL] [Project Page] [Code]

• ReinDiffuse: "ReinDiffuse: Crafting Physically Plausible Motions with Reinforced Diffusion Model". WACV(2025) [URL] [Project Page]

• LaMP: "LaMP: Language-Motion Pretraining for Motion Generation, Retrieval, and Captioning". ICLR(2025) [URL] [Project Page] [Code]

• MotionRL: "MotionRL: Align Text-to-Motion Generation to Human Preferences with Multi-Reward Reinforcement Learning". arXiv(2024) [URL]

• VIM: "A Unified Framework for Motion Reasoning and Generation in Human Interaction". ICCV(2025) [URL] [Project Page]

• DART: "DartControl: A Diffusion-Based Autoregressive Motion Model for Real-Time Text-Driven Motion Control". ICLR(2025) [URL] [Project Page] [Code]

• UniMuMo: "UniMuMo: Unified Text, Music and Motion Generation". arXiv(2024) [URL] [Project Page] [Code]

• Being-M0: "Scaling Large Motion Models with Million-Level Human Motions". ICML(2025) [URL] [Project Page] [Code]

• CLaM: "CLaM: An Open-Source Library for Performance Evaluation of Text-driven Human Motion Generation". MM(24) [URL] [Code]

• L3EM: "Towards Emotion-enriched Text-to-Motion Generation via LLM-guided Limb-level Emotion Manipulating ". MM(2024) [URL] [Code]

• MotionMix: "MotionMix: Weakly-Supervised Diffusion for Controllable Motion Generation". AAAI(2024) [URL] [Project Page] [Code]

• STMC: "Multi-Track Timeline Control for Text-Driven 3D Human Motion Generation". CVPR Workshop(2024) [URL] [Project Page] [Code]

• GUESS: "GUESS:GradUally Enriching SyntheSis for Text-Driven Human Motion Generation". TVCG(2024) [URL] [Code]

• Fg-T2M: "Fg-T2M: Fine-Grained Text-Driven Human Motion Generation via Diffusion Model". ICCV(2023) [URL]

• AttT2M: "AttT2M: Text-Driven Human Motion Generation with Multi-Perspective Attention Mechanism". ICCV(2023) [URL] [Code]

• M2DM: "Priority-Centric Human Motion Generation in Discrete Latent Space". ICCV(2023) [URL]

• ATOM: "Language-guided Human Motion Synthesis with Atomic Actions". MM(2023) [URL] [Code]

• MotionGPT: "MotionGPT: Human Motion as a Foreign Language". NeurIPS(2023) [URL] [Project Page] [Code]

• MotionGPT: "MotionGPT: Finetuned LLMs Are General-Purpose Motion Generators". AAAI(2024) [URL] [Project Page] [Code]

• DiffKFC: "Enhanced Fine-grained Motion Diffusion for Text-driven Human Motion Synthesis". AAAI(2024) [URL]

• GMD: "Guided Motion Diffusion for Controllable Human Motion Synthesis". ICCV(2023) [URL] [Project Page] [Code]

• MAA: "Make-An-Animation: Large-Scale Text-conditional 3D Human Motion Generation". ICCV(2023) [URL] [Project Page]

• AMD: "AMD: Autoregressive Motion Diffusion". AAAI(2024) [URL] [Code]

• TMR: "TMR: Text-to-Motion Retrieval Using Contrastive 3D Human Motion Synthesis". ICCV(2023) [URL] [Project Page] [Code]

• TM2D: "TM2D: Bimodality Driven 3D Dance Generation via Music-Text Integration". ICCV(2023) [URL] [Project Page] [Code]

• ReMoDiffuse: "ReMoDiffuse: Retrieval-Augmented Motion Diffusion Model". ICCV(2023) [URL] [Project Page] [Code]

• priorMDM: "Human Motion Diffusion as a Generative Prior". ICLR(2024) [URL] [Project Page] [Code]

• InsActor: "InsActor: Instruction-driven Physics-based Characters". NeurIPS(2023) [URL] [Project Page] [Code]

• FineMoGen: "FineMoGen: Fine-Grained Spatio-Temporal Motion Generation and Editing". NeurIPS(2023) [URL] [Project Page] [Code]

• PRO-Motion: "Plan, Posture and Go: Towards Open-World Text-to-Motion Generation". ECCV(2024) [URL] [Project Page]

• IterativeEditing: "Iterative Motion Editing with Natural Language". SIGGRAPH(2024) [URL] [Project Page] [Code]

• CrossDiff: "Realistic Human Motion Generation with Cross-Diffusion Models". ECCV(2024) [URL] [Project Page] [Code]

• B2A-HDM: "Towards Detailed Text-to-Motion Synthesis via Basic-to-Advanced Hierarchical Diffusion Model". AAAI(2024) [URL]

• OMG: "OMG: Towards Open-vocabulary Motion Generation via Mixture of Controllers". CVPR(2024) [URL] [Project Page]

• MMM: "MMM: Generative Masked Motion Model". CVPR(2024) [URL] [Project Page] [Code]

• EMDM: "EMDM: Efficient Motion Diffusion Model for Fast and High-Quality Motion Generation". ECCV(2024) [URL] [Project Page] [Code]

• MoMask: "MoMask: Generative Masked Modeling of 3D Human Motions". CVPR(2024) [URL] [Project Page] [Code]

• TLControl: "TLControl: Trajectory and Language Control for Human Motion Synthesis". arXiv(2023) [URL] [Code]

• UDE-2: "A Unified Framework for Multimodal, Multi-Part Human Motion Synthesis". arXiv(2023) [URL] [Project Page] [Code]

• GraphMotion: "Act As You Wish: Fine-Grained Control of Motion Diffusion Model with Hierarchical Semantic Graphs". NeurIPS(2023) [URL] [Code]

• HumanTOMATO: "HumanTOMATO: Text-aligned Whole-body Motion Generation". ICML(2024) [URL] [Project Page] [Code]

• MoConVQ: "MoConVQ: Unified Physics-Based Motion Control via Scalable Discrete Representations". SIGGRAPH(2024) [URL] [Project Page] [Code]

• KP: "Bridging the Gap between Human Motion and Action Semantics via Kinematic Phrases". ECCV(2024) [URL] [Project Page] [Code]

• T2M-GPT: "T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations". CVPR(2023) [URL] [Project Page] [Code]

• Modiff: "Modiff: Action-Conditioned 3D Motion Generation with Denoising Diffusion Probabilistic Models". arXiv(2023) [URL]

• MDM: "Human Motion Diffusion Model". ICLR(2023) [URL] [Project Page] [Code]

• TEACH: "TEACH: Temporal Action Composition for 3D Humans". 3DV(2022) [URL] [Project Page] [Code]

• FLAME: "FLAME: Free-form Language-based Motion Synthesis & Editing". AAAI(2023) [URL] [Project Page] [Code]

• MotionDiffuse: "MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model". TPAMI(2024) [URL] [Project Page] [Code]

• TM2T: "TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Texts". ECCV(2022) [URL] [Project Page] [Code]

• T2M: "Generating Diverse and Natural 3D Human Motions from Text". CVPR(2022) [URL] [Project Page] [Code]

• AvatarCLIP: "AvatarCLIP: Zero-Shot Text-Driven Generation and Animation of 3D Avatars". SIGGRAPH(2022) [URL] [Project Page] [Code]

• TEMOS: "TEMOS: Generating diverse human motions from textual descriptions". ECCV(2022) [URL] [Project Page] [Code]

• ImplicitMotion: "Implicit Neural Representations for Variable Length Human Motion Generation". ECCV(2022) [URL] [Code]

• MotionCLIP: "MotionCLIP: Exposing Human Motion Generation to CLIP Space". ECCV(2022) [URL] [Project Page] [Code]

• MultiAct: "MultiAct: Long-Term 3D Human Motion Generation from Multiple Action Labels". AAAI(2023) [URL] [Code]

• MoFusion: "MoFusion: A Framework for Denoising-Diffusion-based Motion Synthesis". CVPR(2023) [URL] [Project Page]

• MLD: "Executing your Commands via Motion Diffusion in Latent Space". CVPR(2023) [URL] [Project Page] [Code]

• PhysDiff: "PhysDiff: Physics-Guided Human Motion Diffusion Model". ICCV(2023) [URL] [Project Page]

• UDE: "UDE: A Unified Driving Engine for Human Motion Generation". CVPR(2023) [URL] [Project Page] [Code]

• Action-GPT: "Action-GPT: Leveraging Large-scale Language Models for Improved and Generalized Action Generation". ICME(2023) [URL] [Project Page] [Code]

• OOHMG: "Being Comes from Not-being: Open-vocabulary Text-to-Motion Generation with Wordless Training". arXiv(2022) [URL] [Code]

• ACTOR: "Action-Conditioned 3D Human Motion Synthesis with Transformer VAE". ICCV(2021) [URL] [Project Page] [Code]

• Action2Motion: "Action2Motion: Conditioned Generation of 3D Human Motions". MM(2020) [URL] [Project Page] [Code]