awesome-text-to-motion

Motion Generation: A Survey of Generative Approaches and Benchmarks

Multimodal Generative AI with Autoregressive LLMs for Human Motion Understanding and Generation: A Way Forward

Text-driven Motion Generation: Overview, Challenges and Directions

Human Motion Generation: A Survey

X-MoGen: Unified Motion Generation across Humans and Animals

FineMotion: A Dataset and Benchmark with both Spatial and Temporal Annotation for Fine-grained Motion Generation and Editing

SnapMoGen: Human Motion Generation from Expressive Texts

Go to Zero: Towards Zero-shot Motion Generation with Million-scale Data

Generating Attribute-Aware Human Motions from Textual Prompt

From Motion to Behavior: Hierarchical Modeling of Humanoid Generative Behavior Control

Dynamic Motion Blending for Versatile Motion Editing

PersonaBooth: Personalized Text-to-Motion Generation

Motion Anything: Any to Motion Generation

Motion-X++: A Large-Scale Multimodal 3D Whole-body Human Motion Dataset

Text to Blind Motion

Text Motion Translator: A Bi-Directional Model for Enhanced 3D Human Motion Generation from Open-Vocabulary Descriptions

A Unified Framework for Motion Reasoning and Generation in Human Interaction

Scaling Large Motion Models with Million-Level Human Motions

CLaM: An Open-Source Library for Performance Evaluation of Text-driven Human Motion Generation

Towards Emotion-enriched Text-to-Motion Generation via LLM-guided Limb-level Emotion Manipulating

MotionFix: Text-Driven 3D Human Motion Editing

Infinite Motion: Extended Motion Generation via Long Text Instructions

Aligning Human Motion Generation with Human Perceptions

MoDiPO: text-to-motion alignment via AI-feedback-driven Direct Preference Optimization

You Think, You ACT: The New Task of Arbitrary Text to Motion Generation

Large Motion Model for Unified Multi-Modal Motion Generation

Contact-aware Human Motion Generation from Textual Descriptions

Motion Generation from Fine-grained Textual Descriptions

FineMoGen: Fine-Grained Spatio-Temporal Motion Generation and Editing

Motion-X: A Large-scale 3D Expressive Whole-body Human Motion Dataset

AMD: Autoregressive Motion Diffusion

Generating Diverse and Natural 3D Human Motions from Text

The KIT Motion-Language Dataset

X-MoGen: Unified Motion Generation across Humans and Animals

ReMoMask: Retrieval-Augmented Masked Motion Generation

Semantically Consistent Text-to-Motion with Unsupervised Styles

SnapMoGen: Human Motion Generation from Expressive Texts

Go to Zero: Towards Zero-shot Motion Generation with Million-scale Data

MOST: Motion Diffusion Model for Rare Text via Temporal Clip Banzhaf Interaction

MotionGPT3: Human Motion as a Second Modality

Generating Attribute-Aware Human Motions from Textual Prompt

Motion-R1: Chain-of-Thought Reasoning and Reinforcement Learning for Human Motion Generation

MOGO: Residual Quantized Hierarchical Causal Transformer for High-Quality and Real-Time 3D Human Motion Generation

ANT: Adaptive Neural Temporal-Aware Text-to-Motion Model

From Motion to Behavior: Hierarchical Modeling of Humanoid Generative Behavior Control

Absolute Coordinates Make Motion Generation Easy

Towards Robust and Controllable Text-to-Motion via Masked Autoregressive Diffusion

ReAlign: Bilingual Text-to-Motion Generation via Step-Aware Reward-Guided Alignment

GENMO: A GENeralist Model for Human MOtion

Deterministic-to-Stochastic Diverse Latent Feature Mapping for Human Motion Synthesis

UniPhys: Unified Planner and Controller with Diffusion for Flexible Physics-Based Character Control

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

MG-MotionLLM: A Unified Framework for Motion Comprehension and Generation across Multiple Granularities

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

MixerMDM: Learnable Composition of Human Motion Diffusion Models

ReMoGPT: Part-Level Retrieval-Augmented Motion-Language Models

UniTMGE: Uniform Text-Motion Generation and Editing Model via Diffusion

Dynamic Motion Blending for Versatile Motion Editing

Dance Like a Chicken: Low-Rank Stylization for Human Motion Diffusion

Human Motion Unlearning

SimMotionEdit: Text-Based Human Motion Editing with Motion Similarity Prediction

MotionStreamer: Streaming Motion Generation via Diffusion-based Autoregressive Model in Causal Latent Space

GenM$^3$: Generative Pretrained Multi-path Motion Model for Text Conditional Human Motion Generation

Reinforcement learning-based motion imitation for physiologically plausible musculoskeletal motor control

Less is More: Improving Motion Diffusion Models with Sparse Keyframes

SALAD: Skeleton-aware Latent Diffusion for Text-driven Motion Generation and Editing

Progressive Human Motion Generation Based on Text and Few Motion Frames

PersonaBooth: Personalized Text-to-Motion Generation

Motion Anything: Any to Motion Generation

Biomechanics-Guided Residual Approach to Generalizable Human Motion Generation and Estimation

Unlocking Pretrained LLMs for Motion-Related Multimodal Generation: A Fine-Tuning Approach to Unify Diffusion and Next-Token Prediction

Fg-T2M++: LLMs-Augmented Fine-Grained Text Driven Human Motion Generation

MotionLab: Unified Human Motion Generation and Editing via the Motion-Condition-Motion Paradigm

CASIM: Composite Aware Semantic Injection for Text to Motion Generation

SPORT: From Zero-shot Prompts to Real-time Motion Generation

MotionPCM: Real-Time Motion Synthesis with Phased Consistency Model

Free-T2M: Frequency Enhanced Text-to-Motion Diffusion Model With Consistency Loss

FlexMotion: Lightweight, Physics-Aware, and Controllable Human Motion Generation

PackDiT: Joint Human Motion and Text Generation via Mutual Prompting

LS-GAN: Human Motion Synthesis with Latent-space GANs

EnergyMoGen: Compositional Human Motion Generation with Energy-Based Diffusion Model in Latent Space

ScaMo: Exploring the Scaling Law in Autoregressive Motion Generation Model

Light-T2M: A Lightweight and Fast Model for Text-to-motion Generation

The Language of Motion: Unifying Verbal and Non-verbal Language of 3D Human Motion

CoMA: Compositional Human Motion Generation with Multi-modal Agents

SoPo: Text-to-Motion Generation Using Semi-Online Preference Optimization

RMD: A Simple Baseline for More General Human Motion Generation via Training-free Retrieval-Augmented Motion Diffuse

BiPO: Bidirectional Partial Occlusion Network for Text-to-Motion Synthesis

MoTe: Learning Motion-Text Diffusion Model for Multiple Generation Tasks

FTMoMamba: Motion Generation with Frequency and Text State Space Models

VersatileMotion: A Unified Framework for Motion Synthesis and Comprehension

Rethinking Diffusion for Text-Driven Human Motion Generation: Redundant Representations, Evaluation, and Masked Autoregression

Morph: A Motion-free Physics Optimization Framework for Human Motion Generation

KMM: Key Frame Mask Mamba for Extended Motion Generation

Text Motion Translator: A Bi-Directional Model for Enhanced 3D Human Motion Generation from Open-Vocabulary Descriptions

M-Adaptor: Text-driven Whole-body Human Motion Generation

MotionGPT-2: A General-Purpose Motion-Language Model for Motion Generation and Understanding

Pay Attention and Move Better: Harnessing Attention for Interactive Motion Generation and Training-free Editing

LEAD: Latent Realignment for Human Motion Diffusion

MaskControl: Spatio-Temporal Control for Masked Motion Synthesis

ReinDiffuse: Crafting Physically Plausible Motions with Reinforced Diffusion Model

LaMP: Language-Motion Pretraining for Motion Generation, Retrieval, and Captioning

MotionRL: Align Text-to-Motion Generation to Human Preferences with Multi-Reward Reinforcement Learning

A Unified Framework for Motion Reasoning and Generation in Human Interaction

DartControl: A Diffusion-Based Autoregressive Motion Model for Real-Time Text-Driven Motion Control

UniMuMo: Unified Text, Music and Motion Generation

Scaling Large Motion Models with Million-Level Human Motions

CLaM: An Open-Source Library for Performance Evaluation of Text-driven Human Motion Generation

Towards Emotion-enriched Text-to-Motion Generation via LLM-guided Limb-level Emotion Manipulating

Text-driven Human Motion Generation with Motion Masked Diffusion Model

EgoLM: Multi-Modal Language Model of Egocentric Motions

MoGenTS: Motion Generation based on Spatial-Temporal Joint Modeling

Unimotion: Unifying 3D Human Motion Synthesis and Understanding

MaskedMimic: Unified Physics-Based Character Control Through Masked Motion Inpainting

T2M-X: Learning Expressive Text-to-Motion Generation from Partially Annotated Data

MoRAG -- Multi-Fusion Retrieval Augmented Generation for Human Motion

BAD: Bidirectional Auto-regressive Diffusion for Text-to-Motion Generation

Lagrangian Motion Fields for Long-term Motion Generation

TextIM: Part-aware Interactive Motion Synthesis from Text

MotionFix: Text-Driven 3D Human Motion Editing

Autonomous LLM-Enhanced Adversarial Attack for Text-to-Motion

MotionCraft: Crafting Whole-Body Motion with Plug-and-Play Multimodal Controls

M2D2M: Multi-Motion Generation from Text with Discrete Diffusion Models

SMooDi: Stylized Motion Diffusion Model

Local Action-Guided Motion Diffusion Model for Text-to-Motion Generation

SuperPADL: Scaling Language-Directed Physics-Based Control with Progressive Supervised Distillation

InfiniMotion: Mamba Boosts Memory in Transformer for Arbitrary Long Motion Generation

Infinite Motion: Extended Motion Generation via Long Text Instructions

MotionGPT: Human Motion Synthesis with Improved Diversity and Realism via GPT-3 Prompting

MoLA: Motion Generation and Editing with Latent Diffusion Enhanced by Adversarial Training

T2LM: Long-Term 3D Human Motion Generation from Multiple Sentences

Programmable Motion Generation for Open-Set Motion Control Tasks

Motion-Agent: A Conversational Framework for Human Motion Generation with LLMs

A Cross-Dataset Study for Text-based 3D Human Motion Retrieval

M$^3$GPT: An Advanced Multimodal, Multitask Framework for Motion Comprehension and Generation

Learning Generalizable Human Motion Generator with Reinforcement Learning

Shape Conditioned Human Motion Generation with Diffusion Model

StableMoFusion: Towards Robust and Efficient Diffusion-based Motion Generation Framework

Exploring Vision Transformers for 3D Human Motion-Language Models with Motion Patches

MoDiPO: text-to-motion alignment via AI-feedback-driven Direct Preference Optimization

LGTM: Local-to-Global Text-Driven Human Motion Diffusion Model

Efficient Text-driven Motion Generation via Latent Consistency Training

SATO: Stable Text-to-Motion Framework

MotionLCM: Real-time Controllable Motion Generation via Latent Consistency Model

You Think, You ACT: The New Task of Arbitrary Text to Motion Generation

MCM: Multi-condition Motion Synthesis Framework

Exploring Text-to-Motion Generation with Human Preference

MotionChain: Conversational Motion Controllers via Multimodal Prompts

Large Motion Model for Unified Multi-Modal Motion Generation

BAMM: Bidirectional Autoregressive Motion Model

ParCo: Part-Coordinating Text-to-Motion Synthesis

Contact-aware Human Motion Generation from Textual Descriptions

CoMo: Controllable Motion Generation through Language Guided Pose Code Editing

AnySkill: Learning Open-Vocabulary Physical Skill for Interactive Agents

Motion Mamba: Efficient and Long Sequence Motion Generation

MMoFusion: Multi-modal Co-Speech Motion Generation with Diffusion Model

Seamless Human Motion Composition with Blended Positional Encodings

MotionMix: Weakly-Supervised Diffusion for Controllable Motion Generation

Multi-Track Timeline Control for Text-Driven 3D Human Motion Generation

GUESS:GradUally Enriching SyntheSis for Text-Driven Human Motion Generation

InsActor: Instruction-driven Physics-based Characters

FineMoGen: Fine-Grained Spatio-Temporal Motion Generation and Editing

Plan, Posture and Go: Towards Open-World Text-to-Motion Generation

Iterative Motion Editing with Natural Language

Realistic Human Motion Generation with Cross-Diffusion Models

Towards Detailed Text-to-Motion Synthesis via Basic-to-Advanced Hierarchical Diffusion Model

OMG: Towards Open-vocabulary Motion Generation via Mixture of Controllers

MMM: Generative Masked Motion Model

EMDM: Efficient Motion Diffusion Model for Fast and High-Quality Motion Generation

MoMask: Generative Masked Modeling of 3D Human Motions

TLControl: Trajectory and Language Control for Human Motion Synthesis

A Unified Framework for Multimodal, Multi-Part Human Motion Synthesis

Act As You Wish: Fine-Grained Control of Motion Diffusion Model with Hierarchical Semantic Graphs

HumanTOMATO: Text-aligned Whole-body Motion Generation

MoConVQ: Unified Physics-Based Motion Control via Scalable Discrete Representations

Bridging the Gap between Human Motion and Action Semantics via Kinematic Phrases

Fg-T2M: Fine-Grained Text-Driven Human Motion Generation via Diffusion Model

AttT2M: Text-Driven Human Motion Generation with Multi-Perspective Attention Mechanism

Priority-Centric Human Motion Generation in Discrete Latent Space

Language-guided Human Motion Synthesis with Atomic Actions

MotionGPT: Human Motion as a Foreign Language

MotionGPT: Finetuned LLMs Are General-Purpose Motion Generators

Enhanced Fine-grained Motion Diffusion for Text-driven Human Motion Synthesis

Guided Motion Diffusion for Controllable Human Motion Synthesis

Make-An-Animation: Large-Scale Text-conditional 3D Human Motion Generation

AMD: Autoregressive Motion Diffusion

TMR: Text-to-Motion Retrieval Using Contrastive 3D Human Motion Synthesis

TM2D: Bimodality Driven 3D Dance Generation via Music-Text Integration

ReMoDiffuse: Retrieval-Augmented Motion Diffusion Model

Human Motion Diffusion as a Generative Prior

T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations

Modiff: Action-Conditioned 3D Motion Generation with Denoising Diffusion Probabilistic Models

MultiAct: Long-Term 3D Human Motion Generation from Multiple Action Labels

MoFusion: A Framework for Denoising-Diffusion-based Motion Synthesis

Executing your Commands via Motion Diffusion in Latent Space

PhysDiff: Physics-Guided Human Motion Diffusion Model

UDE: A Unified Driving Engine for Human Motion Generation

Action-GPT: Leveraging Large-scale Language Models for Improved and Generalized Action Generation

Being Comes from Not-being: Open-vocabulary Text-to-Motion Generation with Wordless Training

Human Motion Diffusion Model

TEACH: Temporal Action Composition for 3D Humans

FLAME: Free-form Language-based Motion Synthesis & Editing

MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model

TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Texts

Generating Diverse and Natural 3D Human Motions from Text

AvatarCLIP: Zero-Shot Text-Driven Generation and Animation of 3D Avatars

TEMOS: Generating diverse human motions from textual descriptions

Implicit Neural Representations for Variable Length Human Motion Generation

MotionCLIP: Exposing Human Motion Generation to CLIP Space

Action-Conditioned 3D Human Motion Synthesis with Transformer VAE

Action2Motion: Conditioned Generation of 3D Human Motions