Dual-Streams Edge Driven Encoder-Decoder Network for Image Super-Resolution

Single image super-resolution (SR) aims at reconstructing high-resolution (HR) images from low-resolution (LR) ones. One of the most key issues is to recover finer image details of LR images. In this paper, considering the importance of edge prior for image SR, we propose a dual-streams edge driven...

Full description

Saved in:
Bibliographic Details
Main Authors: Feng Li, Huihui Bai, Lijun Zhao, Yao Zhao
Format: Article
Language:English
Published: IEEE 2018-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/8379545/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849722357859483648
author Feng Li
Huihui Bai
Lijun Zhao
Yao Zhao
author_facet Feng Li
Huihui Bai
Lijun Zhao
Yao Zhao
author_sort Feng Li
collection DOAJ
description Single image super-resolution (SR) aims at reconstructing high-resolution (HR) images from low-resolution (LR) ones. One of the most key issues is to recover finer image details of LR images. In this paper, considering the importance of edge prior for image SR, we propose a dual-streams edge driven encoder-decoder network, which combines edge stream-based encoder-decoder network (edge-EDN) and color stream based encoder-decoder network (color-EDN) to reconstruct HR images with more image details. Instead of utilizing two sub-networks to learn edge information and color image contents respectively, a multitask learning framework is developed to jointly train edge-EDN and color-EDN. Therefore, as the structure prior, the reconstructed HR edge maps are fused with learned features of color stream to refine the HR color images. To reconstruct HR images with better visual quality, a total loss function combining edge loss and color loss is designed to make an optimal tradeoff between the image fidelity and texture details. Our extensive benchmark evaluations demonstrate that our method for SR performs better both on high objective quality and human visual perception compared with several state-of-the-art SR methods.
format Article
id doaj-art-deb4e50fb44048119c691c1ae1760ddf
institution DOAJ
issn 2169-3536
language English
publishDate 2018-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-deb4e50fb44048119c691c1ae1760ddf2025-08-20T03:11:22ZengIEEEIEEE Access2169-35362018-01-016334213343110.1109/ACCESS.2018.28463638379545Dual-Streams Edge Driven Encoder-Decoder Network for Image Super-ResolutionFeng Li0Huihui Bai1https://orcid.org/0000-0002-3879-8957Lijun Zhao2Yao Zhao3Institute of Information Science, Beijing Jiaotong University, Beijing, ChinaInstitute of Information Science, Beijing Jiaotong University, Beijing, ChinaInstitute of Information Science, Beijing Jiaotong University, Beijing, ChinaInstitute of Information Science, Beijing Jiaotong University, Beijing, ChinaSingle image super-resolution (SR) aims at reconstructing high-resolution (HR) images from low-resolution (LR) ones. One of the most key issues is to recover finer image details of LR images. In this paper, considering the importance of edge prior for image SR, we propose a dual-streams edge driven encoder-decoder network, which combines edge stream-based encoder-decoder network (edge-EDN) and color stream based encoder-decoder network (color-EDN) to reconstruct HR images with more image details. Instead of utilizing two sub-networks to learn edge information and color image contents respectively, a multitask learning framework is developed to jointly train edge-EDN and color-EDN. Therefore, as the structure prior, the reconstructed HR edge maps are fused with learned features of color stream to refine the HR color images. To reconstruct HR images with better visual quality, a total loss function combining edge loss and color loss is designed to make an optimal tradeoff between the image fidelity and texture details. Our extensive benchmark evaluations demonstrate that our method for SR performs better both on high objective quality and human visual perception compared with several state-of-the-art SR methods.https://ieeexplore.ieee.org/document/8379545/Dual-streamsedge-drivenimage super-resolution (SR)edge streamcolor stream
spellingShingle Feng Li
Huihui Bai
Lijun Zhao
Yao Zhao
Dual-Streams Edge Driven Encoder-Decoder Network for Image Super-Resolution
IEEE Access
Dual-streams
edge-driven
image super-resolution (SR)
edge stream
color stream
title Dual-Streams Edge Driven Encoder-Decoder Network for Image Super-Resolution
title_full Dual-Streams Edge Driven Encoder-Decoder Network for Image Super-Resolution
title_fullStr Dual-Streams Edge Driven Encoder-Decoder Network for Image Super-Resolution
title_full_unstemmed Dual-Streams Edge Driven Encoder-Decoder Network for Image Super-Resolution
title_short Dual-Streams Edge Driven Encoder-Decoder Network for Image Super-Resolution
title_sort dual streams edge driven encoder decoder network for image super resolution
topic Dual-streams
edge-driven
image super-resolution (SR)
edge stream
color stream
url https://ieeexplore.ieee.org/document/8379545/
work_keys_str_mv AT fengli dualstreamsedgedrivenencoderdecodernetworkforimagesuperresolution
AT huihuibai dualstreamsedgedrivenencoderdecodernetworkforimagesuperresolution
AT lijunzhao dualstreamsedgedrivenencoderdecodernetworkforimagesuperresolution
AT yaozhao dualstreamsedgedrivenencoderdecodernetworkforimagesuperresolution