nv-tlabs/vipe
Estimates camera poses and depth maps from videos
View on index · View in 3D Map
Related repos
- Video and image annotation tool for computer vision projects
- monocular depth estimation for endoscopy videos using near-field lighting
- Generates 3D from 2D videos using AI depth mapping
- Tracks 3D points across multiple camera views
- LLM for vision, audio, and language
- Distills vision foundation models into one
- RGB SLAM baseline using monocular depth and Gaussian scene mapping, easy to try out for 3D reconstruction from video
- Generates timelapse videos from UniFi Protect cameras
- NVR interface for RTSP cameras with motion detection and HomeKit support
- dense SLAM with neural implicit encoding for indoor scenes
