Perceptual Fairness in Image Restoration

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Ohayon, Guy, Elad, Michael, Michaeli, Tomer
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866914970304774144
author Ohayon, Guy
Elad, Michael
Michaeli, Tomer
author_facet Ohayon, Guy
Elad, Michael
Michaeli, Tomer
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2405_13805
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Perceptual Fairness in Image Restoration
Ohayon, Guy
Elad, Michael
Michaeli, Tomer
Image and Video Processing
Artificial Intelligence
Computer Vision and Pattern Recognition
Machine Learning
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.
title Perceptual Fairness in Image Restoration
topic Image and Video Processing
Artificial Intelligence
Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2405.13805