Repository logo
 

Dataset and metrics for predicting local visible differences

Simple item page
cam.issuedOnline2018-11-26
dc.contributor.authorWolski, K
dc.contributor.authorGiunchi, D
dc.contributor.authorYe, N
dc.contributor.authorDidyk, P
dc.contributor.authorMyszkowski, K
dc.contributor.authorMantiuk, R
dc.contributor.authorSeidel, HP
dc.contributor.authorSteed, A
dc.contributor.authorMantiuk, RK
dc.date.accessioned2018-07-10T13:22:15Z
dc.date.available2018-07-10T13:22:15Z
dc.date.issued2018
dc.description.abstract<jats:p>A large number of imaging and computer graphics applications require localized information on the visibility of image distortions. Existing image quality metrics are not suitable for this task as they provide a single quality value per image. Existing visibility metrics produce visual difference maps, and are specifically designed for detecting just noticeable distortions but their predictions are often inaccurate. In this work, we argue that the key reason for this problem is the lack of large image collections with a good coverage of possible distortions that occur in different applications. To address the problem, we collect an extensive dataset of reference and distorted image pairs together with user markings indicating whether distortions are visible or not. We propose a statistical model that is designed for the meaningful interpretation of such data, which is affected by visual search and imprecision of manual marking. We use our dataset for training existing metrics and we demonstrate that their performance significantly improves. We show that our dataset with the proposed statistical model can be used to train a new CNN-based metric, which outperforms the existing solutions. We demonstrate the utility of such a metric in visually lossless JPEG compression, super-resolution and watermarking.</jats:p>
dc.identifier.doi10.17863/CAM.25300
dc.identifier.eissn1557-7368
dc.identifier.issn0730-0301
dc.identifier.urihttps://www.repository.cam.ac.uk/handle/1810/277970
dc.language.isoeng
dc.publisherAssociation for Computing Machinery (ACM)
dc.publisher.urlhttp://dx.doi.org/10.1145/3196493
dc.subjectVisual perception
dc.subjectvisual difference predictor
dc.subjectvisual metric
dc.subjectdistortion visibility
dc.subjectimage quality
dc.subjectdata-driven metric
dc.subjectdataset
dc.subjectconvolutional neural network
dc.titleDataset and metrics for predicting local visible differences
dc.typeArticle
dcterms.dateAccepted2018-03-12
prism.issueIdentifier5
prism.publicationDate2018
prism.publicationNameACM Transactions on Graphics
prism.volume37
pubs.funder-project-idEuropean Research Council (725253)
pubs.funder-project-idEuropean Commission Horizon 2020 (H2020) Marie Sklodowska-Curie actions (765911)
rioxxterms.licenseref.startdate2018-11-01
rioxxterms.licenseref.urihttp://www.rioxx.net/licenses/all-rights-reserved
rioxxterms.typeJournal Article/Review
rioxxterms.versionAM
rioxxterms.versionofrecord10.1145/3196493

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
wolski2018local_metric.pdf
Size:
8.01 MB
Format:
Adobe Portable Document Format
Description:
Accepted version
Licence
http://www.rioxx.net/licenses/all-rights-reserved
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
DepositLicenceAgreement.pdf
Size:
417.78 KB
Format:
Adobe Portable Document Format
Download

Collections

Scholarly Works - Computer Science and Technology