xinyiW915/ReLaX-VQA

ReLaX-VQA: Residual Fragment and Layer Stack Extraction for Enhancing Video Quality Assessment

16
/ 100
Experimental

This project helps video content creators, streaming platforms, and quality assurance professionals quickly assess the visual quality of compressed videos, especially user-generated content, without needing an original, uncompressed reference. You input a video file, and it outputs a score reflecting the video's perceived quality. This tool is for anyone who needs to evaluate video quality in situations where the original source video is unavailable.

No commits in the last 6 months.

Use this if you need to objectively score the quality of a video that has already been compressed or processed, such as user-submitted content or videos from a third-party source, and you don't have the original uncompressed file.

Not ideal if you need to compare a video against its uncompressed original to measure the exact impact of a compression algorithm, as this tool is designed for 'no-reference' quality assessment.

video-quality-assessment content-moderation streaming-optimization digital-media post-production
No License Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 6 / 25
Maturity 8 / 25
Community 0 / 25

How are scores calculated?

Stars

20

Forks

Language

Python

License

Last pushed

Jul 21, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/xinyiW915/ReLaX-VQA"

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