Perceptual Fairness in Image Restoration

TL;DR

This paper introduces a new fairness measure for image restoration called Group Perceptual Index (GPI), which compares the distribution of reconstructed images to ground truth, aiming for equal perceptual quality across groups.

Contribution

It proposes a novel, distribution-based fairness metric (GPI) for image restoration and demonstrates its application and advantages over existing definitions.

Findings

GPI effectively measures perceptual fairness across groups.

State-of-the-art algorithms can be evaluated for fairness using GPI.

Theoretical analysis links GPI to previous fairness notions.

Abstract

Fairness in image restoration tasks is the desire to treat different sub-groups of images equally well. Existing definitions of fairness in image restoration are highly restrictive. They consider a reconstruction to be a correct outcome for a group (e.g., women) only if it falls within the group's set of ground truth images (e.g., natural images of women); otherwise, it is considered entirely incorrect. Consequently, such definitions are prone to controversy, as errors in image restoration can manifest in various ways. In this work we offer an alternative approach towards fairness in image restoration, by considering the Group Perceptual Index (GPI), which we define as the statistical distance between the distribution of the group's ground truth images and the distribution of their reconstructions. We assess the fairness of an algorithm by comparing the GPI of different groups, and say that it achieves perfect Perceptual Fairness (PF) if the GPIs of all groups are identical. We motivate and theoretically study our new notion of fairness, draw its connection to previous ones, and demonstrate its utility on state-of-the-art face image restoration algorithms.