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

By Zhenqiang Ying, Haoran Niu, Praful Gupta, Dhruv Kumar Mahajan, Deepti Ghadiyaram, A. Bovik. Computer Vision and Pattern Recognition, 2019

445 citations recorded by the source corpus.

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 40, 000 real-world distorted pictures and 120, 000 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). The dataset and source code are available at https: //live.ece.utexas.edu/research.php.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/631740089f6b72a58d3729df65376584533789d3

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

MUSIQ: Multi-scale Image Quality Transformer (2021, methodology): “It consistently achieves the state-of-the-art performance on three technical quality datasets: PaQ-2-PiQ [41], KonIQ-10k [16], and SPAQ [11], and is on-par with the state-of-the-art on the aesthetic quality dataset AVA [29].”
Exploring Video Quality Assessment on User Generated Contents from Aesthetic and Technical Perspectives (2022, methodology): “765 Patch-VQ (CVPR, 2021) [1] PaQ-2-PiQ [60] 0.”
FAST-VQA: Efficient End-to-end Video Quality Assessment with Fragment Sampling (2022, methodology): “Some methods [40,41] use the features extractor pre-trained with IQA datasets [13,39].”
TOPIQ: A Top-Down Approach From Semantics to Distortions for Image Quality Assessment (2023, methodology): “I, images from three datasets, SPAQ, AVA, and FLIVE, need to be resized.”
No-Reference Image Quality Assessment via Transformers, Relative Ranking, and Self-Consistency (2021, methodology): “Recently, by introducing more in-the-wild datasets such as CLIVE [9], KonIQ-10K [10], and LIVEFB [11] we can have a better understanding of complex distortions ( e.g., poor lighting conditions, sensor limitations, lens imperfections, amateur manipulations) that often occur in real-world images.”
Uncertainty-Aware Blind Image Quality Assessment in the Laboratory and Wild (2020, methodology): “1) Correlation Results: We compare the performance of UNIQUE against three full-reference IQA measures - MSSSIM [2], NLPD [40] and DISTS [41], and ten BIQA models, including four knowledge-driven methods that do not require MOSs for training - NIQE [10], IL-NIQE [26], dipIQ [15] and Ma19 [16], and s”