ucaszyp/STEPS

This is the official repository for ICRA-2023 paper "STEPS: Joint Self-supervised Nighttime Image Enhancement and Depth Estimation"

36
/ 100
Emerging

This tool helps autonomous navigation and robotics engineers improve the perception capabilities of self-driving vehicles or robots operating in low-light conditions. It takes nighttime camera images as input and simultaneously enhances their visibility while estimating the distance to objects in the scene. This is crucial for applications where reliable depth information is needed for safe navigation after dark.

194 stars. No commits in the last 6 months.

Use this if you need to perform accurate depth estimation and image enhancement from a single camera's nighttime footage, especially for autonomous driving or robotic navigation tasks.

Not ideal if your primary need is general-purpose photo enhancement for human viewing rather than precise spatial understanding for machine perception.

autonomous-driving robotics-navigation nighttime-vision depth-perception environmental-sensing
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 10 / 25

How are scores calculated?

Stars

194

Forks

11

Language

Python

License

MIT

Last pushed

Feb 13, 2023

Commits (30d)

0

Get this data via API

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

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