baegwangbin/MaGNet

[CVPR 2022 Oral] Multi-View Depth Estimation by Fusing Single-View Depth Probability with Multi-View Geometry

39
/ 100
Emerging

This project helps computer vision practitioners accurately determine the depth of objects in a scene from multiple camera views. It takes a series of images (video frames) and outputs a precise depth map, indicating how far each object is from the camera. This is ideal for researchers and engineers working on 3D scene reconstruction or autonomous navigation.

236 stars. No commits in the last 6 months.

Use this if you need to generate highly accurate depth maps from multiple viewpoints, especially in challenging environments with reflective or texture-less surfaces.

Not ideal if you only have a single image view and don't require the enhanced accuracy provided by multi-view geometry.

3D-reconstruction autonomous-navigation robotics computer-vision scene-understanding
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 13 / 25

How are scores calculated?

Stars

236

Forks

17

Language

Python

License

MIT

Last pushed

Jun 20, 2022

Commits (30d)

0

Get this data via API

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

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