Deep Feature Statistics Mapping for Generalized Screen Content Image Quality Assessment

计算机科学 人工智能 图像质量 特征(语言学) 模式识别(心理学) 特征提取 图像处理 质量(理念) 计算机视觉 统计 内容(测量理论) 图像(数学) 数学 数学分析 哲学 认识论 语言学
作者
Baoliang Chen,Hanwei Zhu,Lingyu Zhu,Shiqi Wang,Sam Kwong
出处
期刊:IEEE transactions on image processing [Institute of Electrical and Electronics Engineers]
卷期号:33: 3227-3241 被引量:2
标识
DOI:10.1109/tip.2024.3393754
摘要

The statistical regularities of natural images, referred to as natural scene statistics, play an important role in no-reference image quality assessment. However, it has been widely acknowledged that screen content images (SCIs), which are typically computer generated, do not hold such statistics. Here we make the first attempt to learn the statistics of SCIs, based upon which the quality of SCIs can be effectively determined. The underlying mechanism of the proposed approach is based upon the mild assumption that the SCIs, which are not physically acquired, still obey certain statistics that could be understood in a learning fashion. We empirically show that the statistics deviation could be effectively leveraged in quality assessment, and the proposed method is superior when evaluated in different settings. Extensive experimental results demonstrate the Deep Feature Statistics based SCI Quality Assessment (DFSS-IQA) model delivers promising performance compared with existing NR-IQA models and shows a high generalization capability in the cross-dataset settings. The implementation of our method is publicly available at https://github.com/Baoliang93/DFSS-IQA.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
汉堡包应助Siren采纳,获得10
1秒前
美丽梦桃发布了新的文献求助10
1秒前
Li应助鑫炜赵采纳,获得30
1秒前
科研通AI6.1应助yan采纳,获得10
2秒前
2秒前
Jerry发布了新的文献求助10
2秒前
3秒前
哒mao关注了科研通微信公众号
3秒前
3秒前
zzt关闭了zzt文献求助
3秒前
Hello应助白白采纳,获得10
4秒前
赘婿应助桑榆采纳,获得10
4秒前
喜东东发布了新的文献求助10
5秒前
nielu完成签到,获得积分10
5秒前
5秒前
罗鑫完成签到,获得积分10
6秒前
你嵙这个期刊没买应助NWP采纳,获得10
6秒前
敖江风云完成签到,获得积分10
7秒前
科研通AI6.1应助無羡采纳,获得10
7秒前
8秒前
8秒前
8秒前
8秒前
8秒前
skylar发布了新的文献求助10
8秒前
9秒前
9秒前
9秒前
9秒前
李爱国应助科研通管家采纳,获得10
10秒前
10秒前
脑洞疼应助科研通管家采纳,获得30
10秒前
10秒前
mmyhn应助科研通管家采纳,获得20
10秒前
10秒前
隐形曼青应助科研通管家采纳,获得10
10秒前
Ava应助科研通管家采纳,获得30
10秒前
pluto应助科研通管家采纳,获得10
10秒前
Owen应助科研通管家采纳,获得10
10秒前
10秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
Kinesiophobia : a new view of chronic pain behavior 5000
Molecular Biology of Cancer: Mechanisms, Targets, and Therapeutics 3000
First commercial application of ELCRES™ HTV150A film in Nichicon capacitors for AC-DC inverters: SABIC at PCIM Europe 1000
Handbook of pharmaceutical excipients, Ninth edition 800
Signals, Systems, and Signal Processing 610
Digital and Social Media Marketing 600
热门求助领域 (近24小时)
化学 医学 生物 材料科学 工程类 有机化学 内科学 生物化学 物理 计算机科学 纳米技术 遗传学 基因 复合材料 化学工程 物理化学 病理 催化作用 免疫学 量子力学
热门帖子
关注 科研通微信公众号,转发送积分 5993312
求助须知:如何正确求助?哪些是违规求助? 7446290
关于积分的说明 16069199
捐赠科研通 5135574
什么是DOI,文献DOI怎么找? 2754289
邀请新用户注册赠送积分活动 1727538
关于科研通互助平台的介绍 1628814