Visual intelligence for your home.
Chinese version of AI pose reference gallery
RGBD video generation model conditioned on camera input
MapAnything: Universal Feed-Forward Metric 3D Reconstruction
Photorealistic Synthetic Dataset for Holistic Indoor Scene
Official Python inference and LoRA trainer package
NVR with realtime local object detection for IP cameras
Generate Any 3D Scene in Seconds
Sharp Monocular Metric Depth in Less Than a Second
[CVPR 2025 Best Paper Award] VGGT
High-Resolution 3D Human Digitization from A Single Image
A Strong and Easy-to-use Single View 3D Hand+Body Pose Estimator
Hide screen when boss is approaching
Vision-language-action model for robot control via images and text