arrow
返回

Fusion Objective Function on Progressive Super-Resolution Network

delete2023-03-20
delete6
delete
OA
AI
A
Amir Hajian
S
Supavadee Aramvith *
DOI:10.3390/jsan12020026delete
delete原文链接
delete原文求助
delete分享
delete收藏
摘要

摘要

En 中文
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.
Keyword:
image super-resolution
MS-SSIM objective function
fuse objective functions
progressive upsampling framework
residual-in-residual dense block

期刊

Journal of Sensor and Actuator Networks 封面图
Journal of Sensor and Actuator Networks
IF:
4.2
论文数:
611
被引数:
1.6K

机构

C
Chulalongkorn University
学者数:
1.8W
论文数: 1.4W
被引数: 1.5W
引用论文

引用论文

Macular pattern dystrophy and homonymous hemianopia in MELAS syndrome
err2015-03-12
err0
errOAAI
errRadua Kamal-Salah; Isabel Baquero-Aranda; María del Mar Grana-Pérez; Jose Manuel García-Campos
err分享
err收藏
Influence of Resilience on Burnout Syndrome of Faculty Professors韧性对教职教授职业倦怠综合征的影响
err2022-01-14
err0
errOAAI
errBlanca Rosa García-Rivera; Ignacio Alejandro Mendoza-Martínez; Jorge Luis García-Alcaraz; Jesús Everardo Olguín-Tiznado; Claudia Camargo Wilson; Mónica Fernanda Araníbar; Pedro García-Alcaraz
err分享
err收藏
err
IF0
err
err0
PREAI
err
err分享
err收藏
err分享
err收藏
Nurses’ Attitudes Towards People with Dementia: the semantic differential technique
err2006-05-01
err0
PREAI
errKarl-Gustaf Norbergh; Yvonne Helin; Annika Dahl; Ove Hellzén; Kenneth Asplund
err分享
err收藏
Intelligent Machine Vision Model for Defective Product Inspection Based on Machine Learning
err2021-01-28
err68
errOAAI
errBenbarrad, Tajeddine; Salhaoui, Marouane; Kenitar, Soukaina Bakhat; Arioua, Mounir
err分享
err收藏
学者 查看更多内容