Nikolai10/PerCo

PyTorch implementation of PerCo (Towards Image Compression with Perfect Realism at Ultra-Low Bitrates, ICLR 2024)

34
/ 100
Emerging

This project helps anyone working with digital images to drastically reduce file sizes while maintaining a high degree of visual quality. You input an image and get back a much smaller image file that still looks realistic, even at ultra-low bitrates. This is ideal for content creators, web developers, or anyone needing efficient image storage and transmission.

103 stars. No commits in the last 6 months.

Use this if you need to compress images to extremely small file sizes, particularly for web delivery or storage, while prioritizing the perceptual quality and realism over perfect pixel-for-pixel accuracy.

Not ideal if your application requires mathematically perfect image fidelity or if you need to compress images without any risk of introducing subtle creative changes.

image-optimization web-design digital-asset-management content-delivery media-compression
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 9 / 25

How are scores calculated?

Stars

103

Forks

6

Language

Python

License

Apache-2.0

Last pushed

Jan 13, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/Nikolai10/PerCo"

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