Realistic hair simulator for skin lesion images: A novel benchemarking tool
作者：
Highlights：
• A novel benchmarking technique for digital, hair removal using generative adversarial networks.
• The hair is synthesized and embedded into the pre-defined regions according to an arbitrary mask.
• Different loss functions have been investigated to achieve high photo-realism and seamless blending.
摘要
•A novel benchmarking technique for digital, hair removal using generative adversarial networks.•The hair is synthesized and embedded into the pre-defined regions according to an arbitrary mask.•Different loss functions have been investigated to achieve high photo-realism and seamless blending.
论文关键词：Melanoma,Generative adversarial networks,Synthetic,Computer-aided diagnosis,Dermatology
论文评审过程：Received 26 December 2019, Revised 5 June 2020, Accepted 13 July 2020, Available online 15 July 2020, Version of Record 16 July 2020.
论文官网地址：https://doi.org/10.1016/j.artmed.2020.101933
