CSGAN: Cyclic-Synthesized Generative Adversarial Networks for image-to-image transformation
作者：
Highlights：
• Image-to-image transformation network is proposed for face and scene datasets.
• The cyclic-synthesized loss is computed between the synthesized and cycled image.
• The cyclic-synthesized loss enforces constraint to generate more realistic images.
• Four publicly available paired datasets and five state-of-the art methods are used.
• Superior results are observed as compared to the existing methods.
摘要
•Image-to-image transformation network is proposed for face and scene datasets.•The cyclic-synthesized loss is computed between the synthesized and cycled image.•The cyclic-synthesized loss enforces constraint to generate more realistic images.•Four publicly available paired datasets and five state-of-the art methods are used.•Superior results are observed as compared to the existing methods.
论文关键词：Pattern generation,Deep learning,Computer vision,Image-to-image transformation,Generative Adversarial Nets,Cyclic-synthesized loss
论文评审过程：Received 27 July 2019, Revised 22 November 2020, Accepted 1 December 2020, Available online 15 December 2020, Version of Record 29 December 2020.
论文官网地址：https://doi.org/10.1016/j.eswa.2020.114431
