Ensemble based deep networks for image super-resolution

作者：

Highlights：

• We suggest a general super-resolution method by using the ensemble of multiple models to reconstruct high-resolution results.

• We focus on Sparse Coding Network and propose a new state-of-the-art method named Ensemble based Sparse Coding Network.

• A back-projection method is introduced to solve the weights of different ensemble models.

• We accelerate the training of Sparse Coding Network (about 120x faster) by using batch normalization.

摘要

•We suggest a general super-resolution method by using the ensemble of multiple models to reconstruct high-resolution results.•We focus on Sparse Coding Network and propose a new state-of-the-art method named Ensemble based Sparse Coding Network.•A back-projection method is introduced to solve the weights of different ensemble models.•We accelerate the training of Sparse Coding Network (about 120x faster) by using batch normalization.

论文关键词：Super-resolution,Ensemble,Sparse prior,Deep networks

论文评审过程：Received 22 July 2016, Revised 6 January 2017, Accepted 22 February 2017, Available online 2 March 2017, Version of Record 17 March 2017.

论文官网地址：https://doi.org/10.1016/j.patcog.2017.02.027