Total variation constraint GAN for dynamic scene deblurring

作者：

Highlights：

• A total variation constraint GAN for dynamic scene deblurring is proposed.

• Performance of deblur relies on total variation constraint and generator model.

• Generator consists of UPR-Blocks and different kernel sizes convolution layers.

• The total variation constraint GAN has the greatest lower bound.

摘要

•A total variation constraint GAN for dynamic scene deblurring is proposed.•Performance of deblur relies on total variation constraint and generator model.•Generator consists of UPR-Blocks and different kernel sizes convolution layers.•The total variation constraint GAN has the greatest lower bound.

论文关键词：Total variation,Deblur,GAN,Convolution neural network

论文评审过程：Received 30 March 2019, Revised 24 April 2019, Accepted 28 May 2019, Available online 5 June 2019, Version of Record 27 June 2019.

论文官网地址：https://doi.org/10.1016/j.imavis.2019.05.007