nianticlabs/depth-hints

[ICCV 2019] Depth Hints are complementary depth suggestions which improve monocular depth estimation algorithms trained from stereo pairs

40
/ 100
Emerging

This project helps improve the accuracy of depth perception from a single camera image. By combining standard camera images with supplementary 'depth hints' from basic stereo algorithms, it generates more precise depth maps. This tool is for researchers and engineers working on computer vision tasks like autonomous navigation or 3D scene reconstruction.

188 stars. No commits in the last 6 months.

Use this if you need to generate highly accurate depth maps from single camera inputs, especially in scenarios where traditional monocular depth estimation struggles with fine details or thin structures.

Not ideal if your application requires real-time depth estimation without any pre-computation steps or if you only have access to monocular training data without any stereo pairs.

autonomous-vehicles 3d-reconstruction robotics computer-vision scene-understanding
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 14 / 25

How are scores calculated?

Stars

188

Forks

20

Language

Jupyter Notebook

License

Last pushed

May 17, 2021

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/nianticlabs/depth-hints"

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