Deep residual network for face sketch synthesis
作者：
Highlights：
• A face sketch synthesis algorithm on the basis of Deep Residual Network is proposed.
• A plain feedforward convolutional network is introduced to enhance the feature maps.
• Generic visual representation and global structure of the face are clearly presented.
• A heterogeneous database is used to evaluate the proposed algorithm.
• The proposed algorithm is performed favorably with real-world face photos.
摘要
•A face sketch synthesis algorithm on the basis of Deep Residual Network is proposed.•A plain feedforward convolutional network is introduced to enhance the feature maps.•Generic visual representation and global structure of the face are clearly presented.•A heterogeneous database is used to evaluate the proposed algorithm.•The proposed algorithm is performed favorably with real-world face photos.
论文关键词：Face sketch synthesis,Deep learning,Residual learning,Convolutional neural networks
论文评审过程：Received 9 February 2021, Revised 16 June 2021, Accepted 24 September 2021, Available online 15 October 2021, Version of Record 10 November 2021.
论文官网地址：https://doi.org/10.1016/j.eswa.2021.115980
