Stars
Fast and Universal 3D reconstruction model for versatile tasks
[CVPR 2025 Best Paper Award] VGGT: Visual Geometry Grounded Transformer
[NeurIPS 2023] MotionGPT: Human Motion as a Foreign Language, a unified motion-language generation model using LLMs
[ICCV 2025] Official Implementation of Contrastive Flow Matching
Mobius: Text to Seamless Looping Video Generation via Latent Shift
深度学习面试宝典（含数学、机器学习、深度学习、计算机视觉、自然语言处理和SLAM等方向）
主要记录大语言大模型（LLMs） 算法（应用）工程师相关的知识及面试题
[ ECCV 2024 ] MotionLCM: This repo is the official implementation of "MotionLCM: Real-time Controllable Motion Generation via Latent Consistency Model"
Official Implementation of the Paper:Motion-example-controlled Co-speech Gesture Generation Leveraging Large Language Models (Siggraph 2025)
(SIGGRAPH 2024) Official repository for "Taming Diffusion Probabilistic Models for Character Control"
[ICCV 2025] MotionStreamer: Streaming Motion Generation via Diffusion-based Autoregressive Model in Causal Latent Space
The official implementation of Flexible Motion In-betweening with Diffusion Models, SIGGRAPH 2024
The Unity Runtime Env for Characteristics-aware Locomotion Control
SnapMoGen: Human Motion Generation from Expressive Texts [NeurIPS 2025]
Game-RL: Synthesizing Multimodal Verifiable Game Data to Boost VLMs' General Reasoning
Parameterizing Everyday Home Activities Towards 3D Generative Modeling of Human-Object Interactions
[CVPR 2025 Highlight] InterMimic: Towards Universal Whole-Body Control for Physics-Based Human-Object Interactions
[ICLR 2024 Spotlight] Unified Human-Scene Interaction via Prompted Chain-of-Contacts
[CVPR 2025 Oral] TokenHSI: Unified Synthesis of Physical Human-Scene Interactions through Task Tokenization
Official implementation of CVPR24 highlight paper "Move as You Say, Interact as You Can: Language-guided Human Motion Generation with Scene Affordance"
Code release for the paper "DartControl: A Diffusion-Based Autoregressive Motion Model for Real-Time Text-Driven Motion Control"
Official implementation of "PersonaBooth: Personalized Text-to-Motion Generation (CVPR 2025)"