Unsupervised Facial Geometry Learning for Sketch to Photo Synthesis
dc.contributor.author | Kazemi, Hadi | |
dc.contributor.author | Taherkhani, Fariborz | |
dc.contributor.author | Nasrabadi, Nasser M. | |
dc.contributor.editor | Brömme, Arslan | |
dc.contributor.editor | Busch, Christoph | |
dc.contributor.editor | Dantcheva, Antitza | |
dc.contributor.editor | Rathgeb, Christian | |
dc.contributor.editor | Uhl, Andreas | |
dc.date.accessioned | 2019-06-17T10:00:29Z | |
dc.date.available | 2019-06-17T10:00:29Z | |
dc.date.issued | 2018 | |
dc.description.abstract | 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. | en |
dc.identifier.isbn | 978-3-88579-676-4 | |
dc.identifier.pissn | 1617-5468 | |
dc.identifier.uri | https://dl.gi.de/handle/20.500.12116/23810 | |
dc.language.iso | en | |
dc.publisher | Köllen Druck+Verlag GmbH | |
dc.relation.ispartof | BIOSIG 2018 - Proceedings of the 17th International Conference of the Biometrics Special Interest Group | |
dc.relation.ispartofseries | Lecture Notes in Informatics (LNI) - Proceedings, Volume P-283 | |
dc.subject | Sketch-Photo Synthesis | |
dc.subject | Generative Adversarial Networks (GAN) | |
dc.subject | Unsupervised Learning | |
dc.subject | Facial Geometry Learning. | |
dc.title | Unsupervised Facial Geometry Learning for Sketch to Photo Synthesis | en |
dc.type | Text/Conference Paper | |
gi.citation.publisherPlace | Bonn | |
gi.conference.date | 26.-28. September 2018 | |
gi.conference.location | Darmstadt |
Dateien
Originalbündel
1 - 1 von 1
Lade...
- Name:
- BIOSIG_2018_paper_23.pdf
- Größe:
- 2.33 MB
- Format:
- Adobe Portable Document Format