In2I: Unsupervised Multi-Image-to-Image Translation Using Generative Adversarial Networks
2018 24th International Conference on Pattern Recognition (ICPR)(2018)
摘要
In unsupervised image-to-image translation, the goal is to learn the mapping between an input image and an output image using a set of unpaired training images. In this paper, we propose an extension of the unsupervised image-to-image translation problem to multiple input setting. Given a set of paired images from multiple modalities, a transformation is learned to translate the input into a specified domain. For this purpose, we introduce a Generative Adversarial Network (GAN) based framework along with a multi-modal generator structure and a new loss term, latent consistency loss. Through various experiments we show that leveraging multiple inputs generally improves the visual quality of the translated images. Moreover, we show that the proposed method outperforms current state-of-the-art unsupervised image-to-image translation methods.
更多查看译文
关键词
unsupervised multiimage-to-image translation,input image,output image,unpaired training images,multiple input setting,paired images,multimodal generator structure,translated images,multiple inputs,state-of-the-art unsupervised image-to-image translation,generative adversarial network based framework,In2I,GAN
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络