Geometry-Consistent Generative Adversarial Networks for One-Sided Unsupervised Domain Mapping

Unsupervised domain mapping aims to learn a function GXY to translate domain X to Y in the absence of paired examples. Finding the optimal GXY without paired data is an ill-posed problem, so appropriate constraints are required to obtain reasonable solutions. While some prominent constraints such as...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online) Jg. 2019; S. 2422 - 2431
Hauptverfasser: Fu, Huan, Gong, Mingming, Wang, Chaohui, Batmanghelich, Kayhan, Zhang, Kun, Tao, Dacheng
Format: Tagungsbericht Journal Article
Sprache:Englisch
Veröffentlicht: United States IEEE 01.06.2019
Schlagworte:
Deep Learning
Image and Video Synthesis
ISSN:1063-6919, 1063-6919
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Unsupervised domain mapping aims to learn a function GXY to translate domain X to Y in the absence of paired examples. Finding the optimal GXY without paired data is an ill-posed problem, so appropriate constraints are required to obtain reasonable solutions. While some prominent constraints such as cycle consistency and distance preservation successfully constrain the solution space, they overlook the special properties of images that simple geometric transformations do not change the image's semantic structure. Based on this special property, we develop a geometry-consistent generative adversarial network (Gc-GAN), which enables one-sided unsupervised domain mapping. GcGAN takes the original image and its counterpart image transformed by a predefined geometric transformation as inputs and generates two images in the new domain coupled with the corresponding geometry-consistency constraint. The geometry-consistency constraint reduces the space of possible solutions while keep the correct solutions in the search space. Quantitative and qualitative comparisons with the baseline (GAN alone) and the state-of-the-art methods including CycleGAN [66] and DistanceGAN [5] demonstrate the effectiveness of our method.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
equal contribution
ISSN:1063-6919
1063-6919
DOI:10.1109/CVPR.2019.00253