TY - JOUR

T1 - Single Image Super-Resolution Using a Deep Encoder-Decoder Symmetrical Network with Iterative Back Projection

AU - Liu, Heng

AU - Han, Jungong

AU - Hou, Shudong

AU - Shao, Ling

AU - Ruan, Yue

N1 - This is the author’s version of a work that was accepted for publication in Neurocomputing. Changes resulting from the publishing process, such as peer review, editing, corrections, structural formatting, and other quality control mechanisms may not be reflected in this document. Changes may have been made to this work since it was submitted for publication. A definitive version was subsequently published in Neurocomputing, 282, 2018 DOI: 10.1016/j.neucom.2017.12.014

PY - 2018/3

Y1 - 2018/3

N2 - Image super-resolution (SR) usually refers to reconstructing a high resolution (HR) image from a low resolution (LR) image without losing high frequency details or reducing the image quality. Recently, image SR based on convolutional neural network (SRCNN) was proposed and has received much attention due to its end-to-end mapping simplicity and superior performance. This method, however, only using three convolution layers to learn the mapping from LR to HR, usually converges slowly and leads to the size of output image reducing significantly. To address these issues, in this work, we propose a novel deep encoder-decoder symmetrical neural network (DEDSN) for single image SR. This deep network is fully composed of symmetrical multiple layers of convolution and deconvolution and there is no pooling (down-sampling and up-sampling) operations in the whole network so that image details degradation occurred in traditional convolutional frameworks is prevented. Additionally, in view of the success of the iterative back projection (IBP) algorithm in image SR, we further combine DEDSN with IBP network realization in this work. The new DEDSN-IBP model introduces the down sampling version of the ground truth image and calculates the simulation error as the prior guidance. Experimental results on benchmark data sets demonstrate that the proposed DEDSN model can achieve better performance than SRCNN and the improved DEDSN-IBP outperforms the reported state-of-the-art methods.

AB - Image super-resolution (SR) usually refers to reconstructing a high resolution (HR) image from a low resolution (LR) image without losing high frequency details or reducing the image quality. Recently, image SR based on convolutional neural network (SRCNN) was proposed and has received much attention due to its end-to-end mapping simplicity and superior performance. This method, however, only using three convolution layers to learn the mapping from LR to HR, usually converges slowly and leads to the size of output image reducing significantly. To address these issues, in this work, we propose a novel deep encoder-decoder symmetrical neural network (DEDSN) for single image SR. This deep network is fully composed of symmetrical multiple layers of convolution and deconvolution and there is no pooling (down-sampling and up-sampling) operations in the whole network so that image details degradation occurred in traditional convolutional frameworks is prevented. Additionally, in view of the success of the iterative back projection (IBP) algorithm in image SR, we further combine DEDSN with IBP network realization in this work. The new DEDSN-IBP model introduces the down sampling version of the ground truth image and calculates the simulation error as the prior guidance. Experimental results on benchmark data sets demonstrate that the proposed DEDSN model can achieve better performance than SRCNN and the improved DEDSN-IBP outperforms the reported state-of-the-art methods.

KW - Single image super-resolution

KW - Deep encoder-decoder

KW - Symmetrical network

KW - Iterative back projection

U2 - 10.1016/j.neucom.2017.12.014

DO - 10.1016/j.neucom.2017.12.014

M3 - Journal article

VL - 282

SP - 52

EP - 59

JO - Neurocomputing

JF - Neurocomputing

SN - 0925-2312

ER -