Logo des Repositoriums
 
Konferenzbeitrag

Unsupervised Facial Geometry Learning for Sketch to Photo Synthesis

Vorschaubild

Volltext URI

Dokumententyp

Text/Conference Paper

Zusatzinformation

Datum

2018

Zeitschriftentitel

ISSN der Zeitschrift

Bandtitel

Verlag

Köllen Druck+Verlag GmbH

Zusammenfassung

Face 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.

Beschreibung

Kazemi, Hadi; Taherkhani, Fariborz; Nasrabadi, Nasser M. (2018): Unsupervised Facial Geometry Learning for Sketch to Photo Synthesis. BIOSIG 2018 - Proceedings of the 17th International Conference of the Biometrics Special Interest Group. Bonn: Köllen Druck+Verlag GmbH. PISSN: 1617-5468. ISBN: 978-3-88579-676-4. Darmstadt. 26.-28. September 2018

Zitierform

DOI

Tags