Library

eCommons

 

Real-time Image Editing and iOS Application with Convolutional Networks

Simple item page
dc.contributor.authorNiu, Ransen
dc.contributor.chairWeinberger, Kilian Quirin
dc.contributor.committeeMemberSine, Wesley
dc.date.accessioned2018-10-23T13:21:49Z
dc.date.available2018-10-23T13:21:49Z
dc.date.issued2018-05-30
dc.description.abstractThis thesis presents a new image editing approach with convolutional networks to automatically alter the image content with a desired attribute and still keep the image photo-realistic. The proposed image editing approach effectively combines the strengths of two prominent images editing algorithms, conditional Generative Adversarial Networks[16] and Deep Feature Interpolation[19], to be time-efficient, memory-efficient, and user-controllable. We also present an inverted deep convolutional network to facilitate the proposed image editing approach. Lastly, we describe the implementation of this image editing approach in an iOS application and demonstrate that this approach is feasible and practical in real-world applications.
dc.identifier.doihttps://doi.org/10.7298/X48G8HXX
dc.identifier.otherNiu_cornell_0058O_10289
dc.identifier.otherhttp://dissertations.umi.com/cornell:10289
dc.identifier.otherbibid: 10489414
dc.identifier.urihttps://hdl.handle.net/1813/59330
dc.language.isoen_US
dc.subjectImage Editing
dc.subjectComputer science
dc.subjectDeep Learning
dc.subjectConvolutional Network
dc.titleReal-time Image Editing and iOS Application with Convolutional Networks
dc.typedissertation or thesis
dcterms.licensehttps://hdl.handle.net/1813/59810
thesis.degree.disciplineComputer Science
thesis.degree.grantorCornell University
thesis.degree.levelMaster of Science
thesis.degree.nameM.S., Computer Science

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Niu_cornell_0058O_10289.pdf
Size:
59.27 MB
Format:
Adobe Portable Document Format
Download

Collections

Cornell Theses and Dissertations