cvg/pixel-perfect-sfm

Pixel-Perfect Structure-from-Motion with Featuremetric Refinement (ICCV 2021, Best Student Paper Award)

46
/ 100
Emerging

This tool helps improve the precision of 3D models and camera positions generated from a collection of images. By analyzing dense visual features in the images, it refines the 2D keypoints and camera poses, resulting in a more accurate 3D reconstruction and better visual localization, even in challenging environments. It's used by researchers and practitioners in computer vision to get highly accurate 3D scene data from photographs.

1,463 stars. No commits in the last 6 months.

Use this if you need to create highly accurate 3D reconstructions of scenes from a set of images or improve the precision of existing 3D models and camera placements.

Not ideal if you are looking for a simple, off-the-shelf solution for general 3D scanning without requiring high precision or direct control over the underlying computer vision algorithms.

3D-reconstruction photogrammetry computer-vision-research robotics-localization spatial-computing
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 20 / 25

How are scores calculated?

Stars

1,463

Forks

151

Language

C++

License

Apache-2.0

Last pushed

Jul 30, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/cvg/pixel-perfect-sfm"

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