DeepObjStyle: deep object-based photo style transfer

Show simple item record

dc.contributor.author Mastan, Indra Deep
dc.contributor.author Raman, Shanmuganathan
dc.date.accessioned 2020-12-26T13:48:45Z
dc.date.available 2020-12-26T13:48:45Z
dc.date.issued 2020-12
dc.identifier.citation Mastan, Indra Deep and Raman, Shanmuganathan, "DeepObjStyle: deep object-based photo style transfer", arXiv, Cornell University Library, DOI: arXiv:2012.06498, Dec. 2020. en_US
dc.identifier.uri http://arxiv.org/abs/2012.06498
dc.identifier.uri https://repository.iitgn.ac.in/handle/123456789/6154
dc.description.abstract One of the major challenges of style transfer is the appropriate image features supervision between the output image and the input (style and content) images. An efficient strategy would be to define an object map between the objects of the style and the content images. However, such a mapping is not well established when there are semantic objects of different types and numbers in the style and the content images. It also leads to content mismatch in the style transfer output, which could reduce the visual quality of the results. We propose an object-based style transfer approach, called DeepObjStyle, for the style supervision in the training data-independent framework. DeepObjStyle preserves the semantics of the objects and achieves better style transfer in the challenging scenario when the style and the content images have a mismatch of image features. We also perform style transfer of images containing a word cloud to demonstrate that DeepObjStyle enables an appropriate image features supervision. We validate the results using quantitative comparisons and user studies.
dc.description.statementofresponsibility by Indra Deep Mastan and Shanmuganathan Raman
dc.language.iso en_US en_US
dc.publisher Cornell University Library en_US
dc.subject Computer Science en_US
dc.subject Computer Vision en_US
dc.subject Pattern Recognition en_US
dc.title DeepObjStyle: deep object-based photo style transfer en_US
dc.type Pre-Print en_US
dc.relation.journal arXiv


Files in this item

Files Size Format View

There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record

Search Digital Repository


Browse

My Account