Papers › NIMA: Neural Image Assessment

NIMA: Neural Image Assessment

15 Sep 2017arXiv:1709.05424archive 2025-07-28

Hossein Talebi, Peyman Milanfar

Automatically learned quality assessment for images has recently become a hot topic due to its usefulness in a wide variety of applications such as evaluating image capture pipelines, storage techniques and sharing media. Despite the subjective nature of this problem, most existing methods only predict the mean opinion score provided by datasets such as AVA [1] and TID2013 [2]. Our approach differs from others in that we predict the distribution of human opinion scores using a convolutional neural network. Our architecture also has the advantage of being significantly simpler than other methods with comparable performance. Our proposed approach relies on the success (and retraining) of proven, state-of-the-art deep object recognition networks. Our resulting network can be used to not only score images reliably and with high correlation to human perception, but also to assist with adaptation and optimization of photo editing/enhancement algorithms in a photographic pipeline. All this is done without need for a "golden" reference image, consequently allowing for single-image, semantic- and perceptually-aware, no-reference quality assessment.

PaperPDFCode

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

Code

idealo/image-quality-assessment mentioned on GitHubtf report
kentsyx/Neural-IMage-Assessment mentioned on GitHubpytorch report
truskovskiyk/nima.pytorch mentioned on GitHubpytorch 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

Aesthetics Quality AssessmentImage Quality AssessmentVideo Quality Assessment

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Aesthetics Quality Assessment AVA NIMA Accuracy 81.5% #4 of 9 Archive leaderboard report
Image Quality Assessment MSU NR VQA Database NIMA KLCC 0.6745 #8 of 10 Archive leaderboard report
Image Quality Assessment MSU NR VQA Database NIMA PLCC 0.8784 #8 of 10 Archive leaderboard report
Image Quality Assessment MSU NR VQA Database NIMA SRCC 0.8494 #8 of 10 Archive leaderboard report
Video Quality Assessment MSU NR VQA Database NIMA KLCC 0.6745 #15 of 21 Archive leaderboard report
Video Quality Assessment MSU NR VQA Database NIMA PLCC 0.8784 #15 of 21 Archive leaderboard report
Video Quality Assessment MSU NR VQA Database NIMA SRCC 0.8494 #15 of 21 Archive leaderboard report
Video Quality Assessment MSU NR VQA Database NIMA Type NR #15 of 21 Archive leaderboard report
Video Quality Assessment MSU SR-QA Dataset NIMA KLCC 0.20377 #49 of 60 Archive leaderboard report
Video Quality Assessment MSU SR-QA Dataset NIMA PLCC 0.26550 #49 of 60 Archive leaderboard report
Video Quality Assessment MSU SR-QA Dataset NIMA SROCC 0.25887 #49 of 60 Archive leaderboard report
Video Quality Assessment MSU SR-QA Dataset NIMA Type NR #49 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.

Methods

Introduced by this paper: NIMA

NIMA

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