Enhanced Deep Residual Networks for Single Image Super-Resolution
Bee Lim Sanghyun Son Heewon Kim Seungjun Nah Kyoung Mu Lee
Department of ECE, ASRI, Seoul National University, 08826, Seoul, Korea
forestrainee@gmail.com, thstkdgus35@snu.ac.kr, ghimhw@gmail.com
seungjun.nah@gmail.com, kyoungmu@snu.ac.kr
Abstract
Recent research on super-resolution has progressed with
the development of deep convolutional neural networks
(DCNN). In particular, residual learning techniques exhibit
improved performance. In this paper, we develop an en-
hanced deep super-resolution network (EDSR) with perfor-
mance exceeding those of current state-of-the-art SR meth-
ods. The significant performance improvement of our model
is due to optimization by removing unnecessary modules in
conventional residual networks. The performance is further
improved by expanding the model size while we stabilize
the training procedure. We also propose a new multi-scale
deep super-resolution system (MDSR) and training method,
which can reconstruct high-resolution images of different
upscaling factors in a single model. The proposed methods
show superior performance over the state-of-the-art meth-
ods on benchmark datasets and prove its excellence by win-
ning the NTIRE2017 Super-Resolution Challenge [26].
1. Introduction
Image super-resolution (SR) problem, particularly sin-
gle image super-resolution (SISR), has gained increasing
research attention for decades. SISR aims to reconstruct
a high-resolution image I
SR
from a single low-resolution
image I
LR
. Generally, the relationship between I
LR
and
the original high-resolution image I
HR
can vary depending
on the situation. Many studies assume that I
LR
is a bicubic
downsampled version of I
HR
, but other degrading factors
such as blur, decimation, or noise can also be considered for
practical applications.
Recently, deep neural networks [11, 12, 14] provide sig-
nificantly improved performance in terms of peak signal-to-
noise ratio (PSNR) in the SR problem. However, such net-
works exhibit limitations in terms of architecture optimality.
First, the reconstruction performance of the neural network
models is sensitive to minor architectural changes. Also, the
same model achieves different levels of performance by dif-
0853 from DIV2K [26]
HR
(PSNR / SSIM)
Bicubic
(30.80 dB / 0.9537)
VDSR [11]
(32.82 dB / 0.9623)
SRResNet [14]
(34.00 dB / 0.9679)
EDSR+ (Ours)
(34.78 dB / 0.9708)
Figure 1: ×4 Super-resolution result of our single-scale SR
method (EDSR) compared with existing algorithms.
ferent initialization and training techniques. Thus, carefully
designed model architecture and sophisticated optimization
methods are essential in training the neural networks.
Second, most existing SR algorithms treat super-
resolution of different scale factors as independent prob-
lems without considering and utilizing mutual relationships
among different scales in SR. As such, those algorithms re-
quire many scale-specific networks that need to to be trained
independently to deal with various scales. Exceptionally,
1
arXiv:1707.02921v1 [cs.CV] 10 Jul 2017