IIGROUP/MANIQA

[CVPRW oral 2022] MANIQA: Multi-dimension Attention Network for No-Reference Image Quality Assessment

42
/ 100
Emerging

This tool helps you automatically assess the perceptual quality of images, mimicking how a human would rate them, without needing a perfect reference image for comparison. You input an image file, and it outputs a numerical score indicating its quality. This is ideal for professionals who need to quickly evaluate image quality at scale, such as in media production, e-commerce, or digital asset management.

411 stars. No commits in the last 6 months.

Use this if you need an automated and objective way to score image quality, especially for images that may have AI-generated distortions or other complex imperfections, without having an original, perfect version to compare against.

Not ideal if you already have a perfect reference image and want to compare the quality of a distorted version against it, as this tool is specifically designed for 'no-reference' assessment.

image-quality-control digital-asset-management media-production computer-vision content-moderation
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 16 / 25

How are scores calculated?

Stars

411

Forks

45

Language

Python

License

Apache-2.0

Last pushed

Jun 10, 2023

Commits (30d)

0

Get this data via API

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

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