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

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

20 Dec 2019CVPR 2020 6arXiv:1912.10088archive 2025-07-28

Zhenqiang Ying, Haoran Niu, Praful Gupta, Dhruv Mahajan, Deepti Ghadiyaram, Alan Bovik

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).

PaperPDFConference PDFCode

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

baidut/PaQ-2-PiQ mentioned on GitHubpytorch report
fastiqa/fastiqa mentioned on GitHubpytorchNOASSERTION report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Image Quality AssessmentNo-Reference Image Quality AssessmentPredictionVideo Quality Assessment

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Quality Assessment MSU NR VQA Database PaQ-2-PiQ KLCC 0.7079 #7 of 10 Archive leaderboard report
Image Quality Assessment MSU NR VQA Database PaQ-2-PiQ PLCC 0.8549 #7 of 10 Archive leaderboard report
Image Quality Assessment MSU NR VQA Database PaQ-2-PiQ SRCC 0.8705 #7 of 10 Archive leaderboard report
Video Quality Assessment MSU NR VQA Database PaQ-2-PiQ KLCC 0.7079 #13 of 21 Archive leaderboard report
Video Quality Assessment MSU NR VQA Database PaQ-2-PiQ PLCC 0.8549 #13 of 21 Archive leaderboard report
Video Quality Assessment MSU NR VQA Database PaQ-2-PiQ SRCC 0.8705 #13 of 21 Archive leaderboard report
Video Quality Assessment MSU NR VQA Database PaQ-2-PiQ Type NR #13 of 21 Archive leaderboard report
Video Quality Assessment MSU SR-QA Dataset PaQ-2-PiQ KLCC 0.57753 #4 of 60 Archive leaderboard report
Video Quality Assessment MSU SR-QA Dataset PaQ-2-PiQ PLCC 0.70988 #4 of 60 Archive leaderboard report
Video Quality Assessment MSU SR-QA Dataset PaQ-2-PiQ SROCC 0.71167 #4 of 60 Archive leaderboard report
Video Quality Assessment MSU SR-QA Dataset PaQ-2-PiQ Type NR #4 of 60 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections