From Patches to Pictures (PaQ-2-PiQ): Mapping the Perceptual Space of Picture Quality

TL;DR

This paper introduces a large-scale database and deep learning models for no-reference perceptual picture quality prediction, achieving state-of-the-art results and providing both global and local quality assessments.

Contribution

It presents the largest subjective picture quality database and novel deep architectures that predict global and local quality, advancing no-reference image quality assessment.

Findings

Achieved state-of-the-art prediction accuracy.

Developed models producing both global and local quality maps.

Demonstrated effectiveness on real-world distorted images.

Abstract

Blind or no-reference (NR) perceptual picture quality prediction is a difficult, unsolved problem of great consequence to the social and streaming media industries that impacts billions of viewers daily. Unfortunately, popular NR prediction models perform poorly on real-world distorted pictures. To advance progress on this problem, we introduce the largest (by far) subjective picture quality database, containing about 40000 real-world distorted pictures and 120000 patches, on which we collected about 4M human judgments of picture quality. Using these picture and patch quality labels, we built deep region-based architectures that learn to produce state-of-the-art global picture quality predictions as well as useful local picture quality maps. Our innovations include picture quality prediction architectures that produce global-to-local inferences as well as local-to-global inferences (via feedback).