Open Peer Review. Open Publishing. Open Access. Open Discussion. Open Directory. Open Recommendations. Open API. Open Source.
CNNs as Inverse Problem Solvers and Double Network Superresolution
Nov 03, 2017 (modified: Nov 03, 2017)ICLR 2018 Conference Blind Submissionreaders: everyoneShow Bibtex
Abstract:In recent years Convolutional Neural Networks (CNN) have been used extensively for Superresolution (SR). In this paper we use inverse problem and sparse representation solutions to form a mathematical basis for CNN operations. We prove a single neuron is able to provide the optimum solution for inverse problems. Intoducing a new concept called representation Dictionary Duality we show that CNN layers act as sparse representation solvers. In the light of theoretical work we propose a new algorithm which uses two networks with different structures that are separately trained with low and high coherency image patches and prove that it performs faster compared to the state-of-the-art algorithms while not sacrificing from performance.
TL;DR:After proving that a neuron acts as an inverse problem solver for superresolution and a network of neurons is guarantied to provide a solution, we proposed a double network architecture that performs faster than state-of-the-art.
Keywords:superresolution, convolutional neural network, sparse representation, inverse problem
Enter your feedback below and we'll get back to you as soon as possible.