Large Receptive Field Networks for High-Scale Image Super-Resolution

George Seif, Dimitrios Androutsos; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2018, pp. 763-772

Abstract


Convolutional Neural Networks have been the backbone of recent rapid progress in Single-Image Super-Resolution. However, existing networks are very deep with many network parameters, thus having a large memory footprint and being challenging to train. We propose Large Receptive Field Networks which strive to directly expand the receptive field of Super-Resolution networks without increasing depth or parameter count. In particular, we use two different methods to expand the network receptive field: 1-D separable kernels and atrous convolutions. We conduct considerable experiments to study the performance of various arrangement schemes of the 1-D separable kernels and atrous convolution in terms of accuracy (PSNR / SSIM), parameter count, and speed, while focusing on the more challenging high upscaling factors. Extensive benchmark evaluations demonstrate the effectiveness of our approach.

Related Material


[pdf] [arXiv]
[bibtex]
@InProceedings{Seif_2018_CVPR_Workshops,
author = {Seif, George and Androutsos, Dimitrios},
title = {Large Receptive Field Networks for High-Scale Image Super-Resolution},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
month = {June},
year = {2018}
}