Brummi/MonoRec

Official implementation of the paper: MonoRec: Semi-Supervised Dense Reconstruction in Dynamic Environments from a Single Moving Camera (CVPR 2021)

46
/ 100
Emerging

This project helps robotics engineers and autonomous vehicle researchers create detailed 3D maps of dynamic environments using only a single moving camera. It takes in video footage from the camera and outputs a dense 3D reconstruction, including depth information and masks for moving objects, even when the scene is changing. The primary users are researchers developing navigation or perception systems for robots and self-driving cars.

601 stars. No commits in the last 6 months.

Use this if you need to generate high-quality 3D depth maps and identify moving elements from monocular video sequences captured by a moving camera.

Not ideal if you have access to stereo cameras, LiDAR data, or require real-time performance on embedded systems without significant optimization.

robotics autonomous-driving 3d-reconstruction mobile-mapping scene-understanding
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 20 / 25

How are scores calculated?

Stars

601

Forks

89

Language

Python

License

MIT

Last pushed

Mar 17, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/Brummi/MonoRec"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.