ABSTRACT

This paper aims to extend the capability of Cycle-Consistent Adversarial Network (CycleGAN) by equipping it with a conditional constraint and extend it into a multi-style image transfer system that can transfer images among more than two image domains. The conditional constraint is given in the form of the target style feature map instead of a one-hot vector, and has shown to provide better transfer results. The proposed system offers greater flexibility for users to choose the style for image transfer. Experimental results show that such an architecture is not only feasible but also yields good results. The proposed architecture can be extended to other transformation applications, such as facial expressions transfer, face aging, and synthesis of various features.

摘要

本文旨在通过为其配备条件约束来扩展循环一致对抗网络 (CycleGAN) 的能力，并将其扩展为可以在两个以上图像域之间传输图像的多样式图像传输系统。条件约束以目标样式特征图而不是单热向量的形式给出，并已证明可以提供更好的传输结果。所提出的系统为用户选择图像传输样式提供了更大的灵活性。实验结果表明，这种架构不仅可行，而且取得了良好的效果。所提出的体系结构可以扩展到其他转换应用程序，例如面部表情转换、面部老化和各种特征的合成。