RAMT-GAN: Realistic and accurate makeup transfer with generative adversarial network

作者：

Highlights：

• Achieving realistic and accurate automatic makeup transfer.

• Identity preservation loss solves the identity-shift problem.

• Background invariant loss solves the background-change problem.

摘要

•Achieving realistic and accurate automatic makeup transfer.•Identity preservation loss solves the identity-shift problem.•Background invariant loss solves the background-change problem.

论文关键词：Automatic facial makeup,Style transfer,Generative adversarial network,Image-to-image transformation

论文评审过程：Received 9 September 2021, Revised 6 January 2022, Accepted 25 January 2022, Available online 1 February 2022, Version of Record 22 February 2022.

论文官网地址：https://doi.org/10.1016/j.imavis.2022.104400