ScholarMate
English简体中文繁體中文
客服热线:400-1616-289
登录注册
期刊论文

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

Pan, Zhaoqing; Yuan, Feng; Lei, Jianjun*; Fang, Yuming; Shao, Xiao; Kwong, Sam江西财经大学; 天津大学; 西安电子科技大学
IEEE Transactions on Image Processing2022DOI: 10.1109/TIP.2022.3144892
32被引9阅读
引用收藏
分享

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.

学科与关键词

关键词
Image restorationVisualizationImage qualityTask analysisFeature extractionTrainingDistortionNo-reference image quality assessmentvisual compensation restoration networkvisual compensation moduleoptimized asymmetric residual blockerror map lossmulti-level features
相关
加载中…
  • Channel Recombination and Projection Network for Blind Image Quality Measurement
    Shen, Lili; Zhao, Bo; Pan, Zhaoqing*; Peng, Bo*; Kwong, Sam; Lei, JianjunIEEE Transactions on Instrumentation and Measurement, 2022, 71: 2513512.
  • No-Reference Image Quality Assessment by Hallucinating Pristine Features
    Chen, Baoliang; Zhu, Lingyu; Kong, Chenqi; Zhu, Hanwei; Wang, Shiqi*; Li, ZhuIEEE Transactions on Image Processing, 2022, 31: 6139-6151.被引 2
  • EARNet: Error-Aware Reconstruction Network for no-reference image quality assessment
    Zhou, Zhiheng; Zhou, Zenan; Tao, Xiyuan; Chen, Hongjie; Yu, Zerui; Cao, YinglieEXPERT SYSTEMS WITH APPLICATIONS, 2024, 238: 122050.
查看全部 →

发表信息

论文状态
公开发表
期刊
IEEE Transactions on Image Processing
发表日期
2022
卷期
第 31 卷
页码
1613-1627
DOI
10.1109/TIP.2022.3144892
语言
ENGLISH
期刊等级
1区
成果收录
SCIE
资助标注
National Natural Science Foundation of China [61971232]; Natural Science Foundation of Jiangsu Province of China [BK20201391]; Natural Science Foundation of Tianjin [18ZXZNGX00110, 18JCJQJC45800]

作者

  • P

    Pan, Zhaoqing (第一作者)

    nanjing univ informat sci & technol · xidian univ · tianjin univ

  • Y

    Yuan, Feng

    tianjin univ

查看全部 6 位作者收起作者
  • L

    Lei, Jianjun (通讯)

    tianjin univ

  • F

    Fang, Yuming

    jiangxi univ finance & econ

  • S

    Shao, Xiao

    nanjing univ informat sci & technol

  • K

    Kwong, Sam

登录解锁更多功能

  • 收藏这篇,随时在“我的 · 收藏”找回
  • 认领你的成果,生成推广素材
  • 关注作者获取最新成果
  • 加入项目组、协同写作
注册 / 登录

产品服务

  • 科研之友
  • 创新城
  • 科创云

服务支持

  • 帮助中心
  • 隐私政策
  • 服务条款

联系方式

在线客服:【】
客服热线:400-1616-289
电子邮箱:support@scholarmate.com

关注或下载科研之友

微信二维码
微信公众号
客户端下载二维码
下载客户端
科研成果科研人员科研机构科研动态爱瑞思软件

©2026 深圳市科研之友网络服务有限公司

公安备案图标粤公网安备 44030502000213
粤ICP备 16046710 号粤B2-20110417