Stars
[CVPR 2025 Best Paper Award] VGGT: Visual Geometry Grounded Transformer
Code for the project "MegaSaM: Accurate, Fast and Robust Structure and Motion from Casual Dynamic Videos"
[Arxiv-2024] MotionLLM: Understanding Human Behaviors from Human Motions and Videos
[NeurIPS 2023] MotionGPT: Human Motion as a Foreign Language, a unified motion-language generation model using LLMs
This repository contains the official implementation of "The Language of Motion: Unifying Verbal and Non-verbal Language of 3D Human Motion".
Hydra is a framework for elegantly configuring complex applications
[CVPR25 Oral (Top 3.3%)] Official code for paper "Reconstructing Humans with a Biomechanically Accurate Skeleton".
[ICCV 2023] PyTorch Implementation of "MotionBERT: A Unified Perspective on Learning Human Motion Representations"
High-Resolution 3D Assets Generation with Large Scale Hunyuan3D Diffusion Models.
Code for "GVHMR: World-Grounded Human Motion Recovery via Gravity-View Coordinates", Siggraph Asia 2024
Goliath Dataset and Official PyTorch Implementation of RelightableHands, Relightable Gaussian Codec Avatars, and Driving-Signal Aware Full-Body Avatars.
High-resolution models for human tasks.
[ECCV 2024] Official Code for "WHAC: World-grounded Humans and Cameras"
The official repo for ECCV'22 paper: Pose for Everything: Towards Category-Agnostic Pose Estimation
RTMPose series (RTMPose, DWPose, RTMO, RTMW) without mmcv, mmpose, mmdet etc.
YOLOv10: Real-Time End-to-End Object Detection [NeurIPS 2024]
awesome grounding: A curated list of research papers in visual grounding
Fine-Grained Open Domain Image Animation with Motion Guidance
Easily compute clip embeddings and build a clip retrieval system with them
Visualizer for neural network, deep learning and machine learning models
Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"
"Effective Whole-body Pose Estimation with Two-stages Distillation" (ICCV 2023, CV4Metaverse Workshop)
Official Repository for CVPR 2023 paper PointAvatar: Deformable Point-based Head Avatars from Videos.
Official implementation of "Neuralangelo: High-Fidelity Neural Surface Reconstruction" (CVPR 2023)