IsGAN: Identity-sensitive generative adversarial network for face photo-sketch synthesis

作者：

Highlights：

• We propose a novel IsGAN for face photo-sketch synthesis.

• We introduce additional identify information into the adversarial learning.

• We propose an identity recognition loss and verify its validity through experiments.

• Extensive experiments show that our method can retain more identity details.

摘要

•We propose a novel IsGAN for face photo-sketch synthesis.•We introduce additional identify information into the adversarial learning.•We propose an identity recognition loss and verify its validity through experiments.•Extensive experiments show that our method can retain more identity details.

论文关键词：Face photo-sketch synthesis,Image-to-image translation,Generative adversarial networks,Convolutional neural network,Face recognition

论文评审过程：Received 22 June 2020, Revised 24 May 2021, Accepted 29 May 2021, Available online 6 June 2021, Version of Record 17 June 2021.

论文官网地址：https://doi.org/10.1016/j.patcog.2021.108077