megvii-research/CREStereo

Official MegEngine implementation of CREStereo(CVPR 2022 Oral).

44
/ 100
Emerging

This project helps computer vision engineers and robotics developers convert two images of the same scene, taken from slightly different viewpoints, into a detailed 'disparity map'. This map reveals the depth and distance of objects in the scene. It takes a left and right image pair and outputs a disparity map, useful for tasks like 3D reconstruction and autonomous navigation.

599 stars. No commits in the last 6 months.

Use this if you need to precisely measure the depth of objects in a scene from stereo camera input for applications such as robotics, augmented reality, or 3D mapping.

Not ideal if you are looking for a solution to identify objects or classify images, as this focuses specifically on depth estimation.

3D-reconstruction robotics-navigation computer-vision depth-sensing augmented-reality
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 18 / 25

How are scores calculated?

Stars

599

Forks

65

Language

Python

License

Apache-2.0

Last pushed

Feb 10, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/megvii-research/CREStereo"

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