A deep learning method for image super-resolution based on geometric similarity

作者：

Highlights：

• Super resolution with convolutional neural networks and multi-scale similarity.

• Embedded spatial transformer into convolutional neural network (CNN) to align data.

• Enhanced image resolution gradually using a pyramid-shaped CNN.

摘要

•Super resolution with convolutional neural networks and multi-scale similarity.•Embedded spatial transformer into convolutional neural network (CNN) to align data.•Enhanced image resolution gradually using a pyramid-shaped CNN.

论文关键词：Super-resolution,Self-similarity,Deep learning,Spatial transformer networks

论文评审过程：Received 20 June 2017, Revised 14 April 2018, Accepted 5 October 2018, Available online 23 October 2018, Version of Record 30 October 2018.

论文官网地址：https://doi.org/10.1016/j.image.2018.10.003