cuiziteng/ICCV_MAET

🌕 [ICCV 2021] Multitask AET with Orthogonal Tangent Regularity for Dark Object Detection. A self-supervised learning way for low-light image object detection.

40
/ 100
Emerging

This project helps improve object detection in challenging low-light conditions by processing dark images to make objects more visible to computer vision systems. It takes in extremely dark or noisy images and outputs an enhanced version suitable for accurate object recognition and bounding box prediction. It is designed for researchers and engineers working on autonomous systems, surveillance, or any application where precise object identification in poor lighting is critical.

185 stars. No commits in the last 6 months.

Use this if you need to reliably detect objects in images taken in very dark environments where traditional computer vision methods struggle.

Not ideal if your primary need is general image enhancement without a specific focus on object detection, or if you only deal with well-lit imagery.

low-light imaging object detection surveillance autonomous vehicles computer vision
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 14 / 25

How are scores calculated?

Stars

185

Forks

17

Language

Python

License

Apache-2.0

Last pushed

Oct 04, 2023

Commits (30d)

0

Get this data via API

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

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