SYSU-Video/Learning-to-Predict-Object-Wise-Just-Recognizable-Distortion-for-Image-and-Video-Compression

Learning to Predict Object-Wise Just Recognizable Distortion for Image and Video Compression

26
/ 100
Experimental

This project helps video encoding engineers and content platforms optimize image and video compression for machine vision tasks. It takes original images and videos, applies various compression levels, and predicts the 'Just Recognizable Distortion' (JRD) level where an object is still detectable by AI. The output helps identify the lowest possible bitrate without impacting AI recognition, benefiting anyone focused on efficient content delivery for AI applications.

Use this if you need to compress images or videos while ensuring that critical objects remain detectable by machine vision models, aiming for the smallest file size possible without compromising AI recognition performance.

Not ideal if your primary concern is human visual quality or if your content is not intended for machine vision analysis.

video-encoding machine-vision content-delivery-network AI-optimization bitrate-optimization
No Package No Dependents
Maintenance 6 / 25
Adoption 4 / 25
Maturity 16 / 25
Community 0 / 25

How are scores calculated?

Stars

8

Forks

Language

Python

License

MIT

Last pushed

Dec 14, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/SYSU-Video/Learning-to-Predict-Object-Wise-Just-Recognizable-Distortion-for-Image-and-Video-Compression"

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