lok-18/A2RNet

AAAI 2025 | A2RNet: Adversarial Attack Resilient Network for Robust Infrared and Visible Image Fusion

29
/ 100
Experimental

This tool helps improve the clarity and robustness of images by combining information from infrared and visible light cameras. It takes separate infrared and visible images, along with optional pseudo-labels for guidance, and produces a single fused image that is more resilient to 'adversarial attacks'—subtle alterations that can trick AI systems. This is ideal for professionals in fields like surveillance, autonomous driving, or medical imaging who rely on AI for detection and segmentation tasks.

No commits in the last 6 months.

Use this if you need to combine infrared and visible light images into a single, enhanced image that can withstand deliberate attempts to confuse computer vision systems.

Not ideal if you are looking for a general-purpose image fusion tool without a specific need for defense against adversarial attacks, or if you only work with single-modality images.

image fusion computer vision security infrared imaging surveillance systems medical imaging
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 4 / 25

How are scores calculated?

Stars

31

Forks

1

Language

Python

License

MIT

Last pushed

Oct 10, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/lok-18/A2RNet"

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