jhornauer/GrUMoDepth

Gradient-based Uncertainty for Monocular Depth Estimation (ECCV 2022)

34
/ 100
Emerging

This project helps computer vision researchers and robotics engineers evaluate the certainty of depth predictions from a single camera image. It takes a pre-trained monocular depth estimation model and image data (like from the KITTI or NYU Depth V2 datasets) to produce an uncertainty map alongside the depth prediction. This helps users understand how reliable each depth value is in the output.

No commits in the last 6 months.

Use this if you are a researcher or engineer working with monocular depth estimation and need to quantify the confidence or uncertainty of your model's predictions in real-world scenarios.

Not ideal if you are looking for an out-of-the-box application for general depth estimation without needing to analyze prediction uncertainty, or if you don't have existing depth estimation models.

computer-vision robotics autonomous-driving 3D-reconstruction depth-sensing
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 10 / 25

How are scores calculated?

Stars

54

Forks

5

Language

Python

License

Apache-2.0

Last pushed

Sep 07, 2023

Commits (30d)

0

Get this data via API

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

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