From Patches to Pictures (PaQ-2-PiQ): Mapping the Perceptual Space of Picture Quality
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).
PDF Abstract CVPR 2020 PDF CVPR 2020 AbstractCode
Datasets
Results from the Paper
Task | Dataset | Model | Metric Name | Metric Value | Global Rank | Benchmark |
---|---|---|---|---|---|---|
Image Quality Assessment | MSU NR VQA Database | PaQ-2-PiQ | SRCC | 0.8705 | # 7 | |
PLCC | 0.8549 | # 8 | ||||
KLCC | 0.7079 | # 7 | ||||
Video Quality Assessment | MSU NR VQA Database | PaQ-2-PiQ | SRCC | 0.8705 | # 13 | |
PLCC | 0.8549 | # 16 | ||||
KLCC | 0.7079 | # 12 | ||||
Type | NR | # 1 | ||||
Video Quality Assessment | MSU SR-QA Dataset | PaQ-2-PiQ | SROCC | 0.71167 | # 4 | |
PLCC | 0.70988 | # 5 | ||||
KLCC | 0.57753 | # 5 | ||||
Type | NR | # 1 |