Patch2Vec: Globally Consistent Image Patch Representation

dc.contributor.authorFried, Ohaden_US
dc.contributor.authorAvidan, Shaien_US
dc.contributor.authorCohen-Or, Danielen_US
dc.contributor.editorJernej Barbic and Wen-Chieh Lin and Olga Sorkine-Hornungen_US
dc.date.accessioned2017-10-16T05:24:28Z
dc.date.available2017-10-16T05:24:28Z
dc.date.issued2016
dc.description.abstractMany image editing applications rely on the analysis of image patches. In this paper, we present a method to analyze patches by embedding them to a vector space, in which the Euclidean distance reflects patch similarity. Inspired by Word2Vec, we term our approach Patch2Vec. However, there is a significant difference between words and patches. Words have a fairly small and well defined dictionary. Image patches, on the other hand, have no such dictionary and the number of different patch types is not well defined. The problem is aggravated by the fact that each patch might contain several objects and textures. Moreover, Patch2Vec should be universal because it must be able to map never-seen-before texture to the vector space. The mapping is learned by analyzing the distribution of all natural patches. We use Convolutional Neural Networks (CNN) to learn Patch2Vec. In particular, we train a CNN on labeled images with a triplet-loss objective function. The trained network encodes a given patch to a 128D vector. Patch2Vec is evaluated visually, qualitatively, and quantitatively. We then use several variants of an interactive single-click image segmentation algorithm to demonstrate the power of our method.en_US
dc.description.number7
dc.description.sectionheadersRepresenting and Editing Images
dc.description.seriesinformationComputer Graphics Forum
dc.description.volume36
dc.identifier.doi10.1111/cgf.13284
dc.identifier.issn1467-8659
dc.identifier.pages183-194
dc.identifier.urihttps://doi.org/10.1111/cgf.13284
dc.identifier.urihttps://diglib.eg.org:443/handle/10.1111/cgf13284
dc.publisherThe Eurographics Association and John Wiley & Sons Ltd.en_US
dc.subjectI.4.10 [Image Processing and Computer Vision]
dc.subjectImage Representation
dc.subjectMultidimensional
dc.titlePatch2Vec: Globally Consistent Image Patch Representationen_US
Files
Collections