ethz-vlg/mvtracker
Tracks 3D points across multiple camera views
View on index · View in 3D Map
Related repos
- Visualizes and explores 3D models in a browser
- Perceives 3D scenes from videos and photo collections with a persistent state
- tracks any pixel in video with transformer-based model, supports dense and long-term point tracking even through occlusion
- Video dataset containing spatial annotations
- VGGT is a neural network that predicts 3D scene attributes like camera parameters, depth, and point maps from images
- turn any mp4 video into a 3d point cloud in real time
- 3D mapping with multi-sensor support and manual correction
- C++ library for camera and multi-camera rig calibration
- Monitors multiple 3D printer camera feeds in a browser
- Real-time dense SLAM from a single camera using 3D reconstruction priors, with global pose and geometry estimation at 15 FPS
