# Assessing invariance to affine transformations in image quality metrics

arXiv: https://arxiv.org/abs/2407.17927 · HTML: https://mlsanity.com/paper/2407.17927/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 46 references that are in the map.
- First posted on arXiv 25 Jul 2024.

## Builds on (most cited first, 8 of 8)

- [Image Quality Assessment: Unifying Structure and Texture Similarity](https://mlsanity.com/paper/2004.07728/) (2020)
- [An Unsupervised Information-Theoretic Perceptual Quality Metric](https://mlsanity.com/paper/2006.06752/) (2020)
- [Perceptually Optimized Image Rendering](https://mlsanity.com/paper/1701.06641/) (2017)
- [On the relation between statistical learning and perceptual distances](https://mlsanity.com/paper/2106.04427/) (2021)
- [PerceptNet: A Human Visual System Inspired Neural Network for Estimating Perceptual Distance](https://mlsanity.com/paper/1910.12548/) (2019)
- [Derivatives and Inverse of Cascaded Linear+Nonlinear Neural Models](https://mlsanity.com/paper/1711.00526/) (2017)
- [In Praise of Artifice Reloaded: Caution with subjective image quality databases](https://mlsanity.com/paper/1801.09632/) (2018)
- [Statistical evaluation of visual quality metrics for image denoising](https://mlsanity.com/paper/1711.00693/) (2017)

## Built on by (most cited first, 2 of 2)

- [RAID-Database: human Responses to Affine Image Distortions](https://mlsanity.com/paper/2412.10211/) (2024)
- [Parametric PerceptNet: A bio-inspired deep-net trained for Image Quality Assessment](https://mlsanity.com/paper/2412.03210/) (2024)

## Abstract (arXiv)

Subjective image quality metrics are usually evaluated according to the correlation with human opinion in databases with distortions that may appear in digital media. However, these oversee affine transformations which may represent better the changes in the images actually happening in natural conditions. Humans can be particularly invariant to these natural transformations, as opposed to the digital ones. In this work, we propose a methodology to evaluate any image quality metric by assessing their invariance to affine transformations, specifically: rotation, translation, scaling, and changes in spectral illumination. Here, invariance refers to the fact that certain distances should be neglected if their values are below a threshold. This is what we call invisibility threshold of a metric. Our methodology consists of two elements: (1) the determination of a visibility threshold in a subjective representation common to every metric, and (2) a transduction from the distance values of the metric and this common representation. This common representation is based on subjective ratings of readily available image quality databases. We determine the threshold in such common representation (the first element) using accurate psychophysics. Then, the transduction (the second element) can be trivially fitted for any metric: with the provided threshold extension of the method to any metric is straightforward. We test our methodology with some well-established metrics and find that none of them show human-like invisibility thresholds. This means that tuning the models exclusively to predict the visibility of generic distortions may disregard other properties of human vision as for instance invariances or invisibility thresholds. The data and code are publicly available to test other metrics.