chansoopark98/Deep-Visual-SLAM-Monodepth2

Deep based Visual SLAM Project(Depth estimation, Optical flow, Visual inertial odometry)

42
/ 100
Emerging

This project helps robotics engineers and researchers create autonomous systems that can understand their environment from camera feeds. It takes in standard video footage (monocular video sequences) and generates a detailed 3D map of the surroundings, along with the camera's precise movement path within that space. This allows for tasks like navigation, obstacle avoidance, and scene reconstruction using just a single camera.

Use this if you need to determine an autonomous agent's movement and build a 3D understanding of its environment from a single camera's video feed, without relying on complex sensor setups or ground truth data.

Not ideal if your application requires extremely high precision in 3D mapping and pose estimation, or if you already have access to specialized depth sensors like LiDAR.

robotics autonomous-navigation 3d-reconstruction computer-vision slam
No Package No Dependents
Maintenance 6 / 25
Adoption 5 / 25
Maturity 16 / 25
Community 15 / 25

How are scores calculated?

Stars

14

Forks

4

Language

C++

License

MIT

Last pushed

Jan 07, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/chansoopark98/Deep-Visual-SLAM-Monodepth2"

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