Skip to main content

Finding Distractors In Images

Author(s): Fried, Ohad; Shechtman, Eli; Goldman, Dan B; Finkelstein, Adam

Download
To refer to this page use: http://arks.princeton.edu/ark:/88435/pr1sv56
Full metadata record
DC FieldValueLanguage
dc.contributor.authorFried, Ohad-
dc.contributor.authorShechtman, Eli-
dc.contributor.authorGoldman, Dan B-
dc.contributor.authorFinkelstein, Adam-
dc.date.accessioned2021-10-08T19:45:35Z-
dc.date.available2021-10-08T19:45:35Z-
dc.date.issued2015en_US
dc.identifier.citationFried, Ohad, Eli Shechtman, Dan B. Goldman, and Adam Finkelstein. "Finding distractors in images." Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1703-1712. doi: 10.1109/CVPR.2015.7298779en_US
dc.identifier.issn1063-6919-
dc.identifier.urihttps://pixl.cs.princeton.edu/pubs/Fried_2015_FDI/fried2015distractors.pdf-
dc.identifier.urihttp://arks.princeton.edu/ark:/88435/pr1sv56-
dc.description.abstractWe propose a new computer vision task we call “distractor prediction.” Distractors are the regions of an image that draw attention away from the main subjects and reduce the overall image quality. Removing distractors-for example, using in-painting - can improve the composition of an image. In this work we created two datasets of images with user annotations to identify the characteristics of distractors. We use these datasets to train an algorithm to predict distractor maps. Finally, we use our predictor to automatically enhance images.en_US
dc.format.extent1703 - 1712en_US
dc.language.isoen_USen_US
dc.relation.ispartofConference on Computer Vision and Pattern Recognition (CVPR)en_US
dc.rightsAuthor's manuscripten_US
dc.titleFinding Distractors In Imagesen_US
dc.typeConference Articleen_US
dc.identifier.doi10.1109/CVPR.2015.7298779-
dc.identifier.eissn1063-6919-
pu.type.symplectichttp://www.symplectic.co.uk/publications/atom-terms/1.0/conference-proceedingen_US

Files in This Item:
File Description SizeFormat 
FindingDistractorsInImages.pdf3.88 MBAdobe PDFView/Download


Items in OAR@Princeton are protected by copyright, with all rights reserved, unless otherwise indicated.