jhakrraman/rt-xnet

[ICIP 2025] Official implementation of RT-X Net: RGB-Thermal cross attention network for Low-Light Image Enhancement

27
/ 100
Experimental

This project helps improve the clarity and detail in images captured in very dim or low-light conditions. It takes both a standard color image (RGB) and a thermal image of the same scene, combines their information, and produces a single, enhanced image that is much brighter and clearer. This is useful for professionals who rely on visual information from cameras in challenging lighting, such as security personnel, surveillance operators, or industrial inspectors.

Use this if you need to significantly brighten and reveal details in surveillance, security, or inspection images captured in extremely low-light environments, leveraging both visible and thermal camera inputs.

Not ideal if you only have standard color images and no corresponding thermal camera input, or if your primary need is for general image noise reduction rather than extreme low-light enhancement.

low-light imaging surveillance thermal imaging night vision image enhancement
No Package No Dependents
Maintenance 6 / 25
Adoption 6 / 25
Maturity 15 / 25
Community 0 / 25

How are scores calculated?

Stars

22

Forks

Language

Python

License

MIT

Last pushed

Nov 06, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/jhakrraman/rt-xnet"

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