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...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online) Ročník 2019; s. 2422 - 2431
Hlavní autoři:	Fu, Huan, Gong, Mingming, Wang, Chaohui, Batmanghelich, Kayhan, Zhang, Kun, Tao, Dacheng
Médium:	Konferenční příspěvek Journal Article
Jazyk:	angličtina
Vydáno:	United States IEEE 01.06.2019
Témata:	Deep Learning Image and Video Synthesis
ISSN:	1063-6919, 1063-6919
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Popis
Shrnutí:	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.
Bibliografie:	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