Logo des Repositoriums
 

Unsupervised Facial Geometry Learning for Sketch to Photo Synthesis

dc.contributor.authorKazemi, Hadi
dc.contributor.authorTaherkhani, Fariborz
dc.contributor.authorNasrabadi, Nasser M.
dc.contributor.editorBrömme, Arslan
dc.contributor.editorBusch, Christoph
dc.contributor.editorDantcheva, Antitza
dc.contributor.editorRathgeb, Christian
dc.contributor.editorUhl, Andreas
dc.date.accessioned2019-06-17T10:00:29Z
dc.date.available2019-06-17T10:00:29Z
dc.date.issued2018
dc.description.abstractFace sketch-photo synthesis is a critical application in law enforcement and digital entertainment industry where the goal is to learn the mapping between a face sketch image and its corresponding photo-realistic image. However, the limited number of paired sketch-photo training data usually prevents the current frameworks to learn a robust mapping between the geometry of sketches and their matching photo-realistic images. Consequently, in this work, we present an approach for learning to synthesize a photo-realistic image from a face sketch in an unsupervised fashion. In contrast to current unsupervised image-to-image translation techniques, our framework leverages a novel perceptual discriminator to learn the geometry of human face. Learning facial prior information empowers the network to remove the geometrical artifacts in the face sketch.We demonstrate that a simultaneous optimization of the face photo generator network, employing the proposed perceptual discriminator in combination with a texture-wise discriminator, results in a significant improvement in quality and recognition rate of the synthesized photos. We evaluate the proposed network by conducting extensive experiments on multiple baseline sketch-photo datasets.en
dc.identifier.isbn978-3-88579-676-4
dc.identifier.pissn1617-5468
dc.identifier.urihttps://dl.gi.de/handle/20.500.12116/23810
dc.language.isoen
dc.publisherKöllen Druck+Verlag GmbH
dc.relation.ispartofBIOSIG 2018 - Proceedings of the 17th International Conference of the Biometrics Special Interest Group
dc.relation.ispartofseriesLecture Notes in Informatics (LNI) - Proceedings, Volume P-283
dc.subjectSketch-Photo Synthesis
dc.subjectGenerative Adversarial Networks (GAN)
dc.subjectUnsupervised Learning
dc.subjectFacial Geometry Learning.
dc.titleUnsupervised Facial Geometry Learning for Sketch to Photo Synthesisen
dc.typeText/Conference Paper
gi.citation.publisherPlaceBonn
gi.conference.date26.-28. September 2018
gi.conference.locationDarmstadt

Dateien

Originalbündel
1 - 1 von 1
Lade...
Vorschaubild
Name:
BIOSIG_2018_paper_23.pdf
Größe:
2.33 MB
Format:
Adobe Portable Document Format