EDSR:超分辨率新突破：深度残差网络与性能提升

需积分: 50 31 浏览量更新于2024-09-07 1 收藏 5.15MB PDF 举报

"本文主要探讨了超分辨率技术在深度卷积神经网络（DCNN）发展中的最新进展，特别是通过增强深度残差网络（Enhanced Deep Residual Networks, EDSR）。作者Bee Lim、Sanghyun Son、Heewon Kim、Seungjun Nah和Kyoung Mu Lee来自首尔国立大学电子工程系及先进科学与技术研究所，他们针对当前最先进的超分辨率方法提出了创新性的解决方案。 EDSR的核心贡献在于对传统残差网络进行优化，移除了不必要的模块，这显著提升了模型性能。作者强调，这种优化使得EDSR能够超越现有技术，展现出出色的图像重建能力。他们不仅关注模型精度，还扩展了模型规模，同时确保了训练过程的稳定性，从而实现了更高效的学习。此外，文中提出了一种新的多尺度深度超分辨率系统（Multi-Scale Deep Super-Resolution System, MDSR），这是一种创新的架构，它允许在一个单一模型内处理不同放大因子的高分辨率图像重建任务。这种方法进一步提高了模型的灵活性和实用性，能够在不同的应用场景下提供高质量的图像提升效果。通过实验验证，EDSR和MDSR在图像细节恢复、视觉质量以及量化指标上都达到了新的高度，表明了深度学习在超分辨率领域的强大潜力。这些研究成果对于推动超分辨率技术的实际应用和发展具有重要意义，也为后续研究者提供了有价值的参考框架。"

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

from a single low-resolution

image I

. Generally, the relationship between I

and

the original high-resolution image I

can vary depending

on the situation. Many studies assume that I

is a bicubic

downsampled version of I

, 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]

(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,

arXiv:1707.02921v1 [cs.CV] 10 Jul 2017

下载后可阅读完整内容，剩余8页未读，立即下载

LiuZhuangCC

粉丝: 49
资源: 5

EDSR:超分辨率新突破：深度残差网络与性能提升

超分辨率预训练模型weights-edsr-16-x4详细解析

PyTorch实现增强深度残差网络：用于单图像超分辨率

深度学习超分辨率模型综合资源包：EDSR、ESPCN等

EDSR-PyTorch EDSR-Tensorflow EDSR-Matlab 哪个效果好

EDSR-Tensorflow：针对单图像超分辨率的增强型深度残差网络的Tensorflow实现

EDSR-ssim:基于CNN的超分辨率算法（例如EDSR CVPRW2017，RDN CVPR2018，MSRN ECCV2018）中的不同SSIM指标

EDSR-PyTorch:PyTorch版本的论文《增强的深度残差网络用于单图像超分辨率》（CVPRW 2017）

EDSR-PyTorch

EDSR-PyTorch-master.zip

weights-edsr-16-x4.tar.gz

最新资源