alexklwong/adaframe-depth-completion

PyTorch implementation of An Adaptive Framework for Learning Unsupervised Depth Completion (RAL 2021 & ICRA 2021)

28
/ 100
Experimental

This project helps robotics engineers and computer vision researchers generate highly detailed 3D scene data. It takes an RGB image and sparse 3D depth measurements (from sensors like lidar or computational methods like Structure-from-Motion) and produces a dense, complete 3D depth map. This is useful for applications requiring a full understanding of a scene's geometry, such as autonomous navigation or 3D reconstruction.

No commits in the last 6 months.

Use this if you need to create accurate and complete 3D depth maps from images where only partial depth information is available, especially in robotics or autonomous systems.

Not ideal if your application requires only rough depth estimates or if you primarily work with single-image depth prediction without sparse depth inputs.

robotics computer-vision 3d-reconstruction autonomous-navigation depth-sensing
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 16 / 25
Community 7 / 25

How are scores calculated?

Stars

10

Forks

1

Language

License

Last pushed

Jun 01, 2021

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/alexklwong/adaframe-depth-completion"

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