We write your reusable computer vision tools. 💜

A generative world for general-purpose robotics & embodied AI learning.

Industry leading face manipulation platform

OpenMMLab Pose Estimation Toolbox and Benchmark.

High-resolution models for human tasks.

The first AI agent that builds permissionless integrations through reverse engineering platforms' internal APIs.

Efficient 3D human pose estimation in video using 2D keypoint trajectories

An extensive node suite that enables ComfyUI to process 3D inputs (Mesh & UV Texture, etc) using cutting edge algorithms (3DGS, NeRF, etc.)

robosuite: A Modular Simulation Framework and Benchmark for Robot Learning

DepthCrafter: Generating Consistent Long Depth Sequences for Open-world Videos

A novel created autonomously by a team of 10 AI agents

Code of [CVPR 2024] "Animatable Gaussians: Learning Pose-dependent Gaussian Maps for High-fidelity Human Avatar Modeling"

Official Implementation of paper "MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion"

A 3DGS framework for omni urban scene reconstruction and simulation.

No Pose, No Problem: Surprisingly Simple 3D Gaussian Splats from Sparse Unposed Images

unofficial implementation of Comfyui magic clothing

Official PyTorch implementation of "Expressive Whole-Body 3D Gaussian Avatar", ECCV 2024.

[ECCV2024] Relightable 3D Gaussian: Real-time Point Cloud Relighting with BRDF Decomposition and Ray Tracing

3DGS Render by KIRI Engine

Python inverse kinematics based on MuJoCo

UMI on Legs: Making Manipulation Policies Mobile with Manipulation-Centric Whole-body Controllers

[CVPR 2024 🔥] Official implementation of the paper "⏳ Hourglass Tokenizer for Efficient Transformer-Based 3D Human Pose Estimation"

WiLoR: End-to-end 3D hand localization and reconstruction in-the-wild

Blender add-on for writing screenplays and convert them directly into timed storyboards.

A Quadruped Robot Easily Constructed through E-Commerce with Sheet Metal Welding and Machining

Reinforcement learning on general 2D physics environments in JAX.

[CVPR 2024 (Highlight)] Relightable and Animatable Neural Avatar from Sparse-View Video

DroneSplat: 3D Gaussian Splatting for Robust 3D Reconstruction from In-the-Wild Drone Imagery

NoteMap: a handy tool for analyzing, organizing, and finding patterns in text files. It works with PDFs, TXTs, and DOCXs. You can also brainstorm ideas and chat with your notes.