jhakrraman/rt-xnet
[ICIP 2025] Official implementation of RT-X Net: RGB-Thermal cross attention network for Low-Light Image Enhancement
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.
Stars
22
Forks
—
Language
Python
License
MIT
Category
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.
Higher-rated alternatives
cvg/LightGlue
LightGlue: Local Feature Matching at Light Speed (ICCV 2023)
shariqfarooq123/AdaBins
Official implementation of Adabins: Depth Estimation using adaptive bins
amusi/CVPR2026-Papers-with-Code
CVPR 2026 论文和开源项目合集
isl-org/ZoeDepth
Metric depth estimation from a single image
daviddmc/NeSVoR
NeSVoR is a package for GPU-accelerated slice-to-volume reconstruction.