Full-Reference Image Quality Assessment Using Self-Attention and Multiscale Features

Author:

Li Yutong1ORCID,Liao Xiaofeng1ORCID,Zhou Mingliang1ORCID,Ji Cheng2ORCID,Wei Xuekai1ORCID,Yue Hong3ORCID

Affiliation:

1. College of Computer Science, Chongqing University, Chongqing 400044, P. R. China

2. School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing 210094, P. R. China

3. CICT Connected and Intelligent Technologies Co. Ltd, Chongqing 400044, P. R. China

Abstract

In this paper, we construct a deep framework for full-reference image quality assessment (FR-IQA) by combining convolution and self-attention features; this approach effectively uses multiscale features to mimic the image evaluation in human eyes. We achieve the integration of information from local to global. First, convolutional neural network (CNN) and encoder of Swin transformer are used to extract multiscale paired features. Second, for each type of features, we fuse them after converting them to a fixed number of channels. For the fused features, we use the square of the difference between two pixel values at the corresponding channel positions to represent the features of the distortion degree. Then, we introduce a recurrent neural network (RNN) to capture the global features. Finally, for the two types of features, we use the full connection (FC) layer to regress two scores and then add the weights to compute the ultimate perceived score. By training and testing on publicly available FR-IQA datasets, experimental results further validate the superiority of our approach.

Funder

NSFC

National Science Youth Fund of Jiangsu Province

National Key R&D Program of China

National Natural Science Foundation of China

Key Projects of Basic Strengthening Plan

Chongqing Talent

Joint Equipment Pre Research and Key Fund Project of the Ministry of Education

Natural Science Foundation of Chongqing, China

Human Resources and Social Security Bureau Project of Chongqing

Guangdong Oppo Mobile Telecommunications Corporation Ltd.

Publisher

World Scientific Pub Co Pte Ltd

Subject

Electrical and Electronic Engineering,Hardware and Architecture,Electrical and Electronic Engineering,Hardware and Architecture

Cited by 1 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

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