artmortal93/PatchMatchStereo_CUDA

PatchMatch Stereo with Red-Black modifiaction and Row Parallel modification for massively parallel computing

27
/ 100
Experimental

This project helps create detailed 3D models from pairs of stereo images, much like how human eyes perceive depth. It takes two images of the same scene, captured from slightly different angles, and quickly generates a 'depth map' that shows the distance of each point in the scene. This tool is for engineers, researchers, or anyone working in computer vision who needs fast and accurate 3D reconstruction for tasks like robotic navigation or environmental mapping.

No commits in the last 6 months.

Use this if you need to rapidly generate accurate depth maps from stereo image pairs for 3D reconstruction tasks, especially if you have access to a powerful GPU.

Not ideal if you do not have access to a CUDA-enabled GPU or if your workflow involves single images rather than stereo pairs.

3D reconstruction computer vision stereo matching depth sensing robotics
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 8 / 25
Community 13 / 25

How are scores calculated?

Stars

16

Forks

3

Language

C

License

Last pushed

Dec 02, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/artmortal93/PatchMatchStereo_CUDA"

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