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

Hao Tang1 Dan Xu2 Wei Wang3 Yan Yan4 Nicu Sebe1
1University of Trento, 2University of Oxford, 3EPFL, 4Texas State University

In ACCV 2018 Oral


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 (G2GAN), 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 G2GAN, 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 G2GAN achieves superior model capacity and better generation performance comparing with existing image-to-image translation GAN models.

Results on Facades Dataset

Results on AR Face Dataset

Results on Bu3dfe Dataset

Results on RaFD Dataset

Results on Alps Seasons Dataset

Results on Painting Style Dataset


Hao Tang, Dan Xu, Wei Wang, Yan Yan, Nicu Sebe. Dual Generator Generative Adversarial Networks for Multi-Domain Image-to-Image Translation. In ACCV 2018.

  title={Dual Generator Generative Adversarial Networks for Multi-Domain Image-to-Image Translation},
  author={Tang, Hao and Xu, Dan and Wang, Wei and Yan, Yan and Sebe, Nicu},

Related Works