VCRNet: Visual Compensation Restoration Network for No-Reference Image Quality Assessment

图像复原 人工智能 计算机视觉 计算机科学 图像质量 补偿(心理学) 残余物 迭代重建 图像(数学) 质量(理念) 图像处理 生成对抗网络 任务(项目管理) 模式识别(心理学) 质量评定 目视检查 特征提取 失真(音乐) 可视化
作者
Zhaoqing Pan,Feng Yuan,Jianjun Lei,Yuming Fang,Xiao Shao,Sam Kwong
出处
期刊:IEEE transactions on image processing [Institute of Electrical and Electronics Engineers]
卷期号:31: 1613-1627 被引量:193
标识
DOI:10.1109/tip.2022.3144892
摘要

Guided by the free-energy principle, generative adversarial networks (GAN)-based no-reference image quality assessment (NR-IQA) methods have improved the image quality prediction accuracy. However, the GAN cannot well handle the restoration task for the free-energy principle-guided NR-IQA methods, especially for the severely destroyed images, which results in that the quality reconstruction relationship between the distorted image and its restored image cannot be accurately built. To address this problem, a visual compensation restoration network (VCRNet)-based NR-IQA method is proposed, which uses a non-adversarial model to efficiently handle the distorted image restoration task. The proposed VCRNet consists of a visual restoration network and a quality estimation network. To accurately build the quality reconstruction relationship between the distorted image and its restored image, a visual compensation module, an optimized asymmetric residual block, and an error map-based mixed loss function, are proposed for increasing the restoration capability of the visual restoration network. For further addressing the NR-IQA problem of severely destroyed images, the multi-level restoration features which are obtained from the visual restoration network are used for the image quality estimation. To prove the effectiveness of the proposed VCRNet, seven representative IQA databases are used, and experimental results show that the proposed VCRNet achieves the state-of-the-art image quality prediction accuracy. The implementation of the proposed VCRNet has been released at https://github.com/NUIST-Videocoding/VCRNet.
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
刚刚
丘比特的应助被辽沈最美女博采纳,获得10
刚刚
刚刚
壮壮的小胖子完成签到,获得积分10
1秒前
1秒前
大舅大舅好的完成签到 ,获得积分10
1秒前
方曦辉发布了新的文献求助10
1秒前
1秒前
1秒前
2秒前
tl完成签到 ,获得积分10
2秒前
麻辣橙子完成签到,获得积分10
2秒前
mtt发布了新的文献求助20
2秒前
顾矜的应助被yiyi采纳,获得10
2秒前
2秒前
2秒前
April发布了新的文献求助10
2秒前
cyan完成签到,获得积分10
2秒前
打打的应助被阿萌毛毛采纳,获得10
2秒前
木木完成签到,获得积分10
2秒前
充电宝的应助被留胡子的扬采纳,获得10
2秒前
2秒前
wanci的应助被留胡子的扬采纳,获得10
3秒前
等枫红染秋季等相遇完成签到,获得积分20
3秒前
搞怪的逍遥完成签到,获得积分20
3秒前
乐乐的应助被留胡子的扬采纳,获得10
3秒前
ZZzzoi完成签到,获得积分10
3秒前
bububu完成签到,获得积分10
3秒前
搜集达人的应助被留胡子的扬采纳,获得10
3秒前
ayzzdbr发布了新的文献求助10
3秒前
3秒前
3秒前
3秒前
3秒前
kkkkkylinmooner完成签到,获得积分10
3秒前
zimablue发布了新的文献求助10
3秒前
今后的应助被喜悦桥采纳,获得10
3秒前
doctorli发布了新的文献求助20
3秒前
yhh关闭了yhh的文献求助
4秒前
宫夏菡发布了新的文献求助30
4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
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1500
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
John McDowells Bildungstheorie 800
八旗制度の研究 600
Analyses de reconnaissances de dettes passées devant les échevins d'Ypres (1249-1291) 600
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8162816
求助须知:如何正确求助?哪些是违规求助? 9557103
关于积分的说明 21738393
捐赠科研通 7753330
什么是DOI,文献DOI怎么找? 3427963
关于科研通互助平台的介绍 2552742
邀请新用户注册赠送积分活动 2472556