arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1901.04604cs.CV
收藏

用于多域图像到图像翻译的双生成器生成对抗网络

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

University of Trento, Italy(意大利特伦托大学);University of Oxford, United Kingdom(英国牛津大学);École Polytechnique Fédérale de Lausanne, Switzerland(瑞士洛桑联邦理工学院);Texas State University, USA(美国德克萨斯州立大学)

Hao Tang, Dan Xu, Wei Wang, Yan Yan, Nicu Sebe

摘要:

使用生成对抗网络(GANs)进行图像到图像转换的最先进方法可以使用未配对的图像数据学习从一个域到另一个域的映射。然而,这些方法需要为每对图像域训练一个特定的模型,这限制了处理两个以上图像域的可扩展性。此外,这些方法的训练阶段具有模型崩溃的共同问题,这降低了生成图像的质量。为了解决这些问题,我们提出了一个双生成器生成对抗网络($^2$ GAN),这是一个强大的和可扩展的方法,允许执行不成对的图像到图像的翻译多个域使用双生成器在一个单一的模型。此外,我们探索了不同的优化损失,以更好地训练G $^2$ GAN,从而使不成对的图像到图像的翻译具有更高的一致性和更好的稳定性。在六个公开可用的数据集上进行了广泛的实验,这些数据集具有不同的场景,即,建筑物、季节、景观和人脸等图像,证明了所提出的$^2$ GAN与现有的图像-图像转换GAN模型相比,具有更高的模型容量和更好的生成性能。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑