[NeurIPS 2023] MotionGPT: Human Motion as a Foreign Language, a unified motion-language generation model using LLMs

HumanML3D: A large and diverse 3d human motion-language dataset.

Official implementation of "MoMask: Generative Masked Modeling of 3D Human Motions (CVPR2024)"

[SIGGRAPH 2022 Journal Track] AvatarCLIP: Zero-Shot Text-Driven Generation and Animation of 3D Avatars

MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model

(CVPR 2023) Pytorch implementation of “T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations”

[CVPR 2023] Executing your Commands via Motion Diffusion in Latent Space, a fast and high-quality motion diffusion model

Official implementation for "Generating Diverse and Natural 3D Human Motions from Texts (CVPR2022)."

Official PyTorch implementation of the paper "TEMOS: Generating diverse human motions from textual descriptions", ECCV 2022 (Oral)

[ICML 2024] 🍅HumanTOMATO: Text-aligned Whole-body Motion Generation

[ICCV-2023] Official code for work "HumanMAC: Masked Motion Completion for Human Motion Prediction".

[CVPR 2022] PoseTriplet: Co-evolving 3D Human Pose Estimation, Imitation, and Hallucination under Self-supervision (Oral)

List of recent advances for human avatars, including generation, reconstruction, and editing, etc.

An aggregation of human motion understanding research.

[CVPR 2024] Official Implementation of "Seamless Human Motion Composition with Blended Positional Encodings".

The official PyTorch implementation of the paper "MotionGPT: Finetuned LLMs are General-Purpose Motion Generators"

🔥 Motion Anything: Any to Motion Generation

NVIDIA-accelerated packages for arm motion planning and control

[Open-source Project] UniMoCap: community implementation to unify the text-motion datasets (HumanML3D, KIT-ML, and BABEL) and whole-body motion dataset (Motion-X).

Official implementations for "Action2Motion: Conditioned Generation of 3D Human Motions (ACM MultiMedia 2020)"

[ICCV 2025] The official implementation of MotionLab

Official implementation of CVPR24 highlight paper "Move as You Say, Interact as You Can: Language-guided Human Motion Generation with Scene Affordance"

(ECCV 2024) SignAvatars: A Large-scale 3D Sign Language Holistic Motion Dataset and Benchmark

[CVPR 2025] InterAct: Advancing Large-Scale Versatile 3D Human-Object Interaction Generation

[SIGGRAPH 2025] Official implementation of 'Motion Inversion For Video Customization'

[ICCV 2025 (Highlight)] DIMO: Diverse 3D Motion Generation for Arbitrary Objects

Official implementation of the NeurIPS22 paper "HUMANISE: Language-conditioned Human Motion Generation in 3D Scenes"

🔥 [ECCV 2024] Motion Mamba: Efficient and Long Sequence Motion Generation

[ArXiv 26] FRoM-W1: Towards General Humanoid Whole-Body Control with Language Instructions

HyperMotion is a pose guided human image animation framework based on a large-scale video diffusion Transformer.