HediFKIH/ThermoVisSR
ThermoVisSR: Multi-Scale Transformer Network for Super-Resolution of Visible and Thermal Air Images
This project helps surveillance and security professionals enhance low-resolution aerial footage of small drones. It takes blurry visible (RGB) and thermal (infrared) video streams as input and produces high-resolution, clearer images, making it easier to identify and track mini/micro UAVs. This tool is for analysts, drone operators, and security personnel working with aerial surveillance.
Use this if you need to improve the clarity and detail of surveillance footage from drones, especially when dealing with small, distant aerial objects captured in both visible light and thermal spectrums.
Not ideal if you primarily work with ground-based surveillance, other object types, or only require super-resolution for single-modality images.
Stars
11
Forks
1
Language
Python
License
CC0-1.0
Category
Last pushed
Dec 03, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/HediFKIH/ThermoVisSR"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
HasnainRaz/Fast-SRGAN
A Fast Deep Learning Model to Upsample Low Resolution Videos to High Resolution at 30fps
NatLabRockies/sup3r
The Super-Resolution for Renewable Resource Data (sup3r) software uses generative adversarial...
the-database/traiNNer-redux
Deep learning training framework for image super resolution and restoration.
eugenesiow/super-image
Image super resolution models for PyTorch.
movehand/raisr
A Python implementation of RAISR