alexklwong/awesome-state-of-depth-completion

Current state of supervised and unsupervised depth completion methods

30
/ 100
Emerging

This project helps robotics engineers and autonomous vehicle developers accurately perceive 3D environments. It takes an RGB image and a sparse 3D point cloud (from sensors like LiDAR or Structure-from-Motion) as input. The output is a dense, detailed 3D depth map, essential for navigation and object avoidance.

503 stars. No commits in the last 6 months.

Use this if you need to evaluate and compare the performance of various methods for generating dense 3D depth maps from limited sensor data in robotics or autonomous systems.

Not ideal if you are looking for an off-the-shelf software solution or a simple API to integrate into an existing application without deep technical understanding.

robotics autonomous-vehicles 3d-reconstruction computer-vision sensor-fusion
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 8 / 25
Community 12 / 25

How are scores calculated?

Stars

503

Forks

24

Language

License

Last pushed

Mar 16, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/alexklwong/awesome-state-of-depth-completion"

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