From Patches to Pictures (PaQ-2-PiQ): Mapping the Perceptual Space of Picture Quality
This addresses a critical issue for social and streaming media industries affecting billions of viewers daily, but it is incremental as it builds on existing methods with a new dataset and architectural improvements.
The paper tackled the problem of blind perceptual picture quality prediction by introducing the largest subjective picture quality database with about 40,000 real-world distorted pictures and 4 million human judgments, and built deep region-based architectures that achieved state-of-the-art global predictions and local quality maps.
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).