wentaoyuan/pcn

Code for PCN: Point Completion Network in 3DV'18 (Oral)

48
/ 100
Emerging

This project helps researchers and engineers working with 3D scanning data to reconstruct complete object shapes from incomplete scans. It takes a partial 3D point cloud, like a scan with gaps or occlusions, and outputs a dense, fully reconstructed 3D point cloud of the original object. This is ideal for those in robotics, computer vision, or 3D modeling who need to work with full object geometries.

477 stars. No commits in the last 6 months.

Use this if you need to automatically fill in missing data or 'complete' the shape of 3D objects represented as point clouds.

Not ideal if your primary need is not 3D shape completion, but rather 3D object detection or classification from complete point clouds.

3D-reconstruction robotics computer-vision autonomous-driving 3D-modeling
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 22 / 25

How are scores calculated?

Stars

477

Forks

86

Language

Python

License

MIT

Last pushed

Nov 09, 2023

Commits (30d)

0

Get this data via API

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

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