ohayonguy/information-estimation-metric

[ICLR 2026] Official implementation of the paper: Learning a distance measure from the information-estimation geometry of data

29
/ 100
Experimental

This project provides a method to calculate a sophisticated distance metric between image pairs, moving beyond simple pixel comparisons. It takes in two images and outputs a numerical score representing their 'information-estimation' distance. Researchers and practitioners in image processing, computer vision, and machine learning can use this to evaluate image similarity or distortion.

Use this if you need a nuanced way to measure similarity or distortion between images, especially when traditional metrics like PSNR don't capture perceptual differences accurately.

Not ideal if you are looking for a straightforward image comparison tool for general users, as it requires familiarity with diffusion models and Python for implementation.

image-quality-assessment perceptual-similarity computer-vision image-analysis
No Package No Dependents
Maintenance 10 / 25
Adoption 4 / 25
Maturity 15 / 25
Community 0 / 25

How are scores calculated?

Stars

8

Forks

Language

Python

License

MIT

Last pushed

Mar 09, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/ohayonguy/information-estimation-metric"

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