Visual intelligence for your home.
Chinese version of AI pose reference gallery
RGBD video generation model conditioned on camera input
An agent skill that finds where a photo was taken
Open source driver assistance system
VGGSfM: Visual Geometry Grounded Deep Structure From Motion
Open-source AI assistant ecosystem with MCP integrations
Fast and Universal 3D reconstruction model for versatile tasks
Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Pass
MapAnything: Universal Feed-Forward Metric 3D Reconstruction
NVR with realtime local object detection for IP cameras
Sharp Monocular Metric Depth in Less Than a Second
Photorealistic Synthetic Dataset for Holistic Indoor Scene
Official Python inference and LoRA trainer package
Generate Any 3D Scene in Seconds
Uncommon Objects in 3D dataset
Lightweight Python library for adding real-time multi-object tracking
[CVPR 2025 Best Paper Award] VGGT
Advancing Open-source World Models
Open Source Differentiable Computer Vision Library
Tooling for the Common Objects In 3D dataset
Database system for building simpler and faster AI-powered application
High-Resolution 3D Human Digitization from A Single Image
Real-time face swap for PC streaming or video calls
A walk along memory lane