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

Perception-Oriented U-Shaped Transformer Network for 360-Degree No-Reference Image Quality Assessment

Zhou, Mingliang; Chen, Lei; Wei, Xuekai*; Liao, Xingran; Mao, Qin*; Wang, Heqiang; Pu, Huayan; Luo, Jun; Xiang, Tao; Fang, Bin重庆大学; xk
IEEE Transactions on Broadcasting2023-6DOI: 10.1109/TBC.2022.3231101
8被引10阅读
引用收藏
分享

摘要

Generally, 360-degree images have absolute senses of reality and three-dimensionality, providing a wide range of immersive interactions. Due to the novel rendering and display technology of 360-degree images, they have more complex perceptual characteristics than other images. It is challenging to perform comprehensive image quality assessment (IQA) learning by simply stacking multichannel neural network architectures for pre/postprocessing, compression, and rendering tasks. To thoroughly learn the global and local features in 360-degree images, reduce the complexity of multichannel neural network models and simplify the training process, this paper proposes a joint architecture with user perception and an efficient transformer dedicated to 360-degree no-reference (NR) IQA. The input of the proposed method is a 360-degree cube map projection (CMP) image. Furthermore, the proposed 360-degree NRIQA method includes a saliency map-based non-overlapping self-attention selection module and a U-shaped transformer (U-former)-based feature extraction module to account for perceptual region importance and projection distortion. The transformer-based architecture and the weighted average technique are jointly utilized for predicting local perceptual quality. Experimental results obtained on widely used databases show that the proposed model outperforms other state-of-the-art methods in NR 360-degree image quality evaluation cases. Furthermore, a cross-database evaluation and an ablation study also demonstrate the inherent robustness and generalization ability of the proposed model.

学科与关键词

关键词
Image quality assessmentno-reference image quality assessment360-degree imageU-shaped transformer
相关
加载中…

文献加载失败,请重试

重试

发表信息

论文状态
公开发表
期刊
IEEE Transactions on Broadcasting
发表日期
2023-06
卷期
第 69 卷, 第 2 期
页码
396-405
DOI
10.1109/TBC.2022.3231101
语言
ENGLISH
成果收录
SCIE
资助标注
National Natural Science Foundation of China [62176027]; General Program of the National Natural Science Foundation of Chongqing [cstc2020jcyj-msxmX0790]; Fundamental Research Funds for the Central Universities [2021CDJJMRH-014]; Human Resources and Social Security Bureau Project of Chongqing [cx2020073]; Huawei Project [H20210586]; Suzhou Institute of USTC [H20201528]; Youth Project of Guizhou Education Department [[2017] 359]; University-Level Scientific Research Projects [qnsy2018028]; Guizhou Provincial Education Department Young Science and Technology Talents Development Project [[2020] 210]

作者

  • Z

    Zhou, Mingliang (第一作者)

    chongqing univ

  • C

    Chen, Lei

    chongqing univ

查看全部 10 位作者收起作者
  • W

    Wei, Xuekai (通讯)

    chongqing univ

  • L

    Liao, Xingran

  • M

    Mao, Qin (通讯)

    qiannan normal univ nationalities · qiannan normal coll nationalities

  • W

    Wang, Heqiang

    chongqing univ

  • P

    Pu, Huayan

    chongqing univ

  • L

    Luo, Jun

    chongqing univ

  • X

    Xiang, Tao

    chongqing univ

  • F

    Fang, Bin

    chongqing univ

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