Dual Generator Generative Adversarial Networks for Multi-domain Image-to-Image Translation

State-of-the-art methods for image-to-image translation with Generative Adversarial Networks (GANs) can learn a mapping from one domain to another domain using unpaired image data. However, these methods require the training of one specific model for every pair of image domains, which limits the scalability in dealing with more than two image domains. In addition, the training stage of these methods has the common problem of model collapse that degrades the quality of the generated images. To tackle these issues, we propose a Dual Generator Generative Adversarial Network (G(2)GAN), which is a robust and scalable approach allowing to perform unpaired image-to-image translation for multiple domains using only dual generators within a single model. Moreover, we explore different optimization losses for better training of G(2)GAN, and thus make unpaired image-to-image translation with higher consistency and better stability. Extensive experiments on six publicly available datasets with different scenarios, i.e., architectural buildings, seasons, landscape and human faces, demonstrate that the proposed G(2)GAN achieves superior model capacity and better generation performance comparing with existing image-to-image translation GAN models.


Published in:
Computer Vision - Accv 2018, Pt I, 11361, 3-21
Presented at:
14th Asian Conference on Computer Vision (ACCV), Perth, AUSTRALIA, December 02-06, 2018
Year:
Jan 01 2019
Publisher:
Cham, SPRINGER INTERNATIONAL PUBLISHING AG
ISSN:
0302-9743
1611-3349
ISBN:
978-3-030-20886-8
978-3-030-20887-5
Keywords:
Laboratories:




 Record created 2019-11-08, last modified 2019-11-08


Rate this document:

Rate this document:
1
2
3
 
(Not yet reviewed)