I noticed that some researchers have compiled excellent summaries of motion generation papers. I recommend referring to the following collections:

• awesome-text-to-motion

• Awesome-Human-Interaction-Motion-Generation

Together, these summaries cover nearly all motion generation papers.

This repository will no longer be updated.

Awesome-Human-Motion-Generation

A list of awesome human motion generation papers. Continuing to be updated!!!

Papers

⭐️ indicates that the paper introduces a new dataset.

Action-to-Motion

• MultiAct: Long-Term 3D Human Motion Generation from Multiple Action Labels, AAAI 2023 | Code

• Action-conditioned On-demand Motion Generation, MM 2022 | Project | Code

• Action-Conditioned 3D Human Motion Synthesis with Transformer VAE, ICCV 2021 | Project | Code

• BABEL: Bodies, Action and Behavior with English Labels, CVPR 2021 | Project | Code ⭐️

• Action2Motion: Conditioned Generation of 3D Human Motions, MM 2020 | Project | Code

Text-to-Motion

• MotionLCM: Real-time Controllable Motion Generation via Latent Consistency Model, ECCV 2024 | Project | Code

• AvatarGPT: All-in-One Framework for Motion Understanding, Planning, Generation and Beyond, CVPR 2024 | Project | Code

• MoMask: Generative Masked Modeling of 3D Human Motions, CVPR 2024 | Project | Code

• HumanTOMATO: Text-aligned Whole-body Motion Generation, ICML 2024 | Project | Code

• MotionGPT: Human Motion as Foreign Language, NeurIPS 2023 | Project | Code

• FineMoGen: Fine-Grained Spatio-Temporal Motion Generation and Editing, NeurIPS 2023 | Project | Code

• Motion-X: A Large-scale 3D Expressive Whole-body Human Motion Dataset, NeurIPS 2023 | Project | Code ⭐️

• ReMoDiffuse: Retrieval-Augmented Motion Diffusion Model, ICCV 2023 | Project | Code

• UDE: A Unified Driving Engine for Human Motion Generation, CVPR 2023 | Project | Code

• T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations, CVPR 2023 | Project | Code

• Executing your Commands via Motion Diffusion in Latent Space, CVPR 2023 | Project | Code

• SINC: Spatial Composition of 3D Human Motions for Simultaneous Action Generation, ICCV 2023 | Project | Code

• FLAME: Free-form Language-based Motion Synthesis & Editing, AAAI 2023 | Project | Code

• Human Motion Diffusion Model, ICLR 2023 | Project | Code

• MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model, ArXiv 2022 | Project | Code

• TEACH: Temporal Action Composition for 3D Humans, 3DV 2022 | Project | Code

• TEMOS: Generating Diverse Human Motions from Textual Descriptions, ECCV 2022 | Project | Code

• TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Texts, ECCV 2022 | Project | Code

• MotionCLIP: Exposing Human Motion Generation to CLIP Space, ECCV 2022 | Project | Code

• Generating Diverse and Natural 3D Human Motions from Text, CVPR 2022 | Project | Code ⭐️

• AMASS: Archive of Motion Capture As Surface Shapes, ICCV 2019 | Project | Code ⭐️

• Synthesis of Compositional Animations from Textual Descriptions, ICCV 2021 | Code

• Language2Pose: Natural Language Grounded Pose Forecasting, 3DV 2019 | Project | Code

Audio-to-Motion

• Emotional Speech-driven 3D Body Animation via Disentangled Latent Diffusion, CVPR 2024 | Project | Code

• Listen, Denoise, Action! Audio-Driven Motion Synthesis with Diffusion Models, TOG 2023 | Project | Code

• Music-Driven Group Choreography, CVPR 2023 | Project | Code ⭐️

• EDGE: Editable Dance Generation From Music, CVPR 2023 | Project | Code

• Generating Holistic 3D Human Motion from Speech, CVPR 2023 | Project | Code

• DanceFormer: Music Conditioned 3D Dance Generation with Parametric Motion Transformer, AAAI 2022 | Code

• Audio2Gestures: Generating Diverse Gestures from Speech Audio with Conditional Variational Autoencoders, ICCV 2021 | Code

• Dancing to Music, NeurIPS 2019 | Code

Object-to-Motion (HOI)

• CORE4D: A 4D Human-Object-Human Interaction Dataset for Collaborative Object REarrangement, ArXiv 2024 | Project | Code ⭐️

• Full-Body Articulated Human-Object Interaction, ICCV 2023 | Project | Code ⭐️

• IMos: Intent-Driven Full-Body Motion Synthesis for Human-Object Interactions, Eurographics 2023 | Project | Code

• Object Motion Guided Human Motion Synthesis, SIGGRAPH Asia 2023 | Project | Code ⭐️

• SAGA: Stochastic Whole-Body Grasping With Contact, ECCV 2022 | Project | Code

• COUCH: Towards Controllable Human-Chair Interactions, ECCV 2022 | Project | Code ⭐️

• BEHAVE: Dataset and Method for Tracking Human Object Interactions, CVPR 2022 | Project ⭐️

• GOAL: Generating 4D Whole-Body Motion for Hand-Object Grasping, CVPR 2022 | Project | Code

• Learning to Sit: Synthesizing Human-Chair Interactions via Hierarchical Control, AAAI 2021 | Project

• GRAB: A Dataset of Whole-Body Human Grasping of Objects, ECCV 2020 | Project | Code ⭐️

Scene-to-Motion (HSI)

• Scaling Up Dynamic Human-Scene Interaction Modeling, CVPR 2024 | Project | Code ⭐️

• Synthesizing Diverse Human Motions in 3D Indoor Scenes, ICCV 2023 | Project | Code

• Narrator: Towards Natural Control of Human-Scene Interaction Generation via Relationship Reasoning, ICCV 2023 | Project

• CIRCLE: Capture in Rich Contextual Environments, CVPR 2023 | Project ⭐️

• Generating Continual Human Motion in Diverse 3D Scenes, 3DV 2023

• Diffusion-based Generation, Optimization, and Planning in 3D Scenes, CVPR 2023 | Project | Code

• Towards Diverse and Natural Scene-aware 3D Human Motion Synthesis, CVPR 2022

• Scene-aware Generative Network for Human Motion Synthesis, CVPR 2021

• Synthesizing Long-Term 3D Human Motion and Interaction in 3D Scenes, CVPR 2021 | Project | Code

• Stochastic Scene-Aware Motion Prediction, ICCV 2021 | Project | Code

• Long-term Human Motion Prediction with Scene Context, ECCV 2020 | Project | Code ⭐️

Multi-Human Generation

• CrowdMoGen: Zero-Shot Text-Driven Collective Motion Generation, ArXiv 2024 | Project | Code

• ReGenNet: Towards Human Action-Reaction Synthesis, CVPR 2024 | Project | Code

• Inter-X: Towards Versatile Human-Human Interaction Analysis, CVPR 2024 | Project | Code ⭐️

• InterGen: Diffusion-based Multi-human Motion Generation under Complex Interactions, IJCV 2024 | Project | Code ⭐️

Multi-Modal Conditional Motion Generation

• Generating Human Interaction Motions in Scenes with Text Control, ECCV 2024 | Project | Code

• Controllable Human-Object Interaction Synthesis, ECCV 2024 | Project

• CG-HOI: Contact-Guided 3D Human-Object Interaction Generation, CVPR 2024 | Project

• Generating Human Motion in 3D Scenes from Text Descriptions, CVPR 2024 | Project | Code

• Move as You Say, Interact as You Can: Language-guided Human Motion Generation with Scene Affordance, CVPR 2024 | Project | Code

• HOI-Diff: Text-Driven Synthesis of 3D Human-Object Interactions using Diffusion Models, ArXiv 2023 | Project | Code

• HUMANISE: Language-conditioned Human Motion Generation in 3D Scenes, NeurIPS 2022 | Project | Code ⭐️

Open-vocabulary & Open-World

• Plan, Posture and Go: Towards Open-World Text-to-Motion Generation, CVPR 2024 | Project

• Programmable Motion Generation for Open-Set Motion Control Tasks, CVPR 2024 | Project | Code

• OMG: Towards Open-vocabulary Motion Generation via Mixture of Controllers, CVPR 2024 | Project

• Being Comes from Not-being: Open-vocabulary Text-to-Motion Generation with Wordless Training, CVPR 2023

Physics-based Human Motion

• CooHOI: Learning Cooperative Human-Object Interaction with Manipulated Object Dynamics, ArXiv 2024

• Anyskill: Learning openvocabulary physical skill for interactive agents, CVPR 2024 | Project | Code

• Unified Human-Scene Interaction via Prompted Chain-of-Contacts, ICLR 2024 | Project | Code

• Synthesizing Physically Plausible Human Motions in 3D Scenes, 3DV 2024 | Project | Code

• Synthesizing Physical Character-Scene Interactions, SIGGRAPH 2023 | Project

• PhysHOI: Physics-Based Imitation of Dynamic Human-Object Interaction, ArXiv 2023 | Project | Code

• InsActor: Instruction-driven Physics-based Characters, NeurIPS 2023 | Project | Code

• ASE: Large-Scale Reusable Adversarial Skill Embeddings for Physically Simulated Characters, SIGGRAPH 2022 | Project | Code

• AMP: Adversarial Motion Priors for Stylized Physics-Based Character Control, SIGGRAPH 2021 | Project | Code

• DeepMimic: Example-Guided Deep Reinforcement Learning of Physics-Based Character Skills, SIGGRAPH 2018 | Project | Code

Others

• Interactive Character Control with Auto-Regressive Motion Diffusion Models, SIGGRAPH 2024 | Project | Code

• WANDR: Intention-guided Human Motion Generation, CVPR 2024 | Project | Code

• MAS: Multi-view Ancestral Sampling for 3D motion generation using 2D diffusion, CVPR 2024 | Project | Code

• Optimizing Diffusion Noise Can Serve As Universal Motion Priors, CVPR 2024 | Project | Code

• GMD: Controllable Human Motion Synthesis via Guided Diffusion Models, ICCV 2023 | Project | Code

• PhysDiff: Physics-Guided Human Motion Diffusion Model, ICCV 2023 | Project

• Trace and Pace: Controllable Pedestrian Animation via Guided Trajectory Diffusion, CVPR 2023 | Project | Code

Contributing

Please feel free to pull requests to add papers. I will merge your PR as soon as possible once it is checked.

License

This repository is distributed under the terms of the MIT license. See LICENSE for details.

Contact

If you have any questions, please feel free to contact me via [email protected].