Fusion Objective Function on Progressive Super-Resolution Network

Author:

Hajian Amir1,Aramvith Supavadee2ORCID

Affiliation:

1. Department of Electrical Engineering, Chulalongkorn University, Bangkok 10330, Thailand

2. Multimedia Data Analytics and Processing Research Unit, Department of Electrical Engineering, Chulalongkorn University, Bangkok 10330, Thailand

Abstract

Recent advancements in Single-Image Super-Resolution (SISR) have explored the network architecture of deep-learning models to achieve a better perceptual quality of super-resolved images. However, the effect of the objective function, which contributes to improving the performance and perceptual quality of super-resolved images, has not gained much attention. This paper proposes a novel super-resolution architecture called Progressive Multi-Residual Fusion Network (PMRF), which fuses the learning objective functions of L2 and Multi-Scale SSIM in a progressively upsampling framework structure. Specifically, we propose a Residual-in-Residual Dense Blocks (RRDB) architecture on a progressively upsampling platform that reconstructs the high-resolution image during intermediate steps in our super-resolution network. Additionally, the Depth-Wise Bottleneck Projection allows high-frequency information of early network layers to be bypassed through the upsampling modules of the network. Quantitative and qualitative evaluation of benchmark datasets demonstrate that the proposed PMRF super-resolution algorithm with novel fusion objective function (L2 and MS-SSIM) improves our model’s perceptual quality and accuracy compared to other state-of-the-art models. Moreover, this model demonstrates robustness against noise degradation and achieves an acceptable trade-off between network efficiency and accuracy.

Funder

Graduate School of Chulalongkorn University

Thailand Science research and Innovation Fund Chulalongkorn University

NSRF via the Program Management Unit for Human Resources & Institutional Development, Research and Innovation

Publisher

MDPI AG

Subject

Control and Optimization,Computer Networks and Communications,Instrumentation

Cited by 4 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. A Robust Approach to COVID-19 CT-Scan Image Denoising with Inception Residual Attention UNET;2024 21st International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology (ECTI-CON);2024-05-27

2. MSRFSR: Multi-Stage Refining Face Super-Resolution With Iterative Collaboration Between Face Recovery and Landmark Estimation;IEEE Access;2024

3. Non-Local Technique on Deep Attentive Face Super-Resolution Network;2023 22nd International Symposium on Communications and Information Technologies (ISCIT);2023-10-16

4. DANS: Deep Attention Network for Single Image Super-Resolution;IEEE Access;2023

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3