Multi-Scale Deep Neural Networks for Real Image Super-Resolution

Shangqi Gao, Xiahai Zhuang; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2019, pp. 0-0

Abstract


Single image super-resolution (SR) is extremely difficult if the upscaling factors of image pairs are unknown and different from each other, which is common in real image SR. To tackle the difficulty, we develop two multi-scale deep neural networks (MsDNN) in this work. Firstly, due to the high computation complexity in high-resolution spaces, we process an input image mainly in two different downscaling spaces, which could greatly lower the usage of GPU memory. Then, to reconstruct the details of an image, we design a multi-scale residual network (MsRN) in the downscaling spaces based on the residual blocks. Besides, we propose a multi-scale dense network based on the dense blocks to compare with MsRN. Finally, our empirical experiments show the robustness of MsDNN for image SR when the upscaling factor is unknown. According to the preliminary results of NTIRE 2019 image SR challenge, our team (ZXHresearch@fudan) ranks 21-st among all participants. The implementation of MsDNN is released at: https://github.com/shangqigao/gsq-image-SR

Related Material


[pdf] [dataset]
[bibtex]
@InProceedings{Gao_2019_CVPR_Workshops,
author = {Gao, Shangqi and Zhuang, Xiahai},
title = {Multi-Scale Deep Neural Networks for Real Image Super-Resolution},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
month = {June},
year = {2019}
}