Zero-shot unsupervised image-to-image translation via exploiting semantic attributes

作者：

Highlights：

• A framework for zero-shot unsupervised image-to-image translation

• Preserving semantic relations to the visual space

• Expanding attribute space using attribute vectors of unseen classes

• Capable of fashion design task

摘要

•A framework for zero-shot unsupervised image-to-image translation•Preserving semantic relations to the visual space•Expanding attribute space using attribute vectors of unseen classes•Capable of fashion design task

论文关键词：Image-to-image translation,Image synthesis,Zero-shot learning,Generative adversarial networks

论文评审过程：Received 4 July 2021, Revised 16 March 2022, Accepted 19 May 2022, Available online 26 May 2022, Version of Record 18 June 2022.

论文官网地址：https://doi.org/10.1016/j.imavis.2022.104489