Fast deep parallel residual network for accurate super resolution image processing

作者：

Highlights：

• New deep 35 convolutional layers structure without loss explosion.

• More accurate SR performance than current state-of-the-art methods.

• Real time application and human-eye recognition at execution speed of 27 fps.

摘要

•New deep 35 convolutional layers structure without loss explosion.•More accurate SR performance than current state-of-the-art methods.•Real time application and human-eye recognition at execution speed of 27 fps.

论文关键词：Super-resolution,Deep convolutional network,Residual learning

论文评审过程：Received 15 September 2018, Revised 17 March 2019, Accepted 17 March 2019, Available online 26 March 2019, Version of Record 30 March 2019.

论文官网地址：https://doi.org/10.1016/j.eswa.2019.03.032