• 综合
  • 标题
  • 关键词
  • 摘要
  • 学者
  • 期刊-刊名
  • 期刊-ISSN
  • 会议名称
搜索

作者:

Gu, Ke (Gu, Ke.) (学者:顾锞) | Jakhetiya, Vinit (Jakhetiya, Vinit.) | Qiao, Jun-Fei (Qiao, Jun-Fei.) (学者:乔俊飞) | Li, Xiaoli (Li, Xiaoli.) (学者:李晓理) | Lin, Weisi (Lin, Weisi.) | Thalmann, Daniel (Thalmann, Daniel.)

收录:

EI Scopus SCIE

摘要:

New challenges have been brought out along with the emerging of 3D-related technologies, such as virtual reality, augmented reality (AR), and mixed reality. Free viewpoint video (FVV), due to its applications in remote surveillance, remote education, and so on, based on the flexible selection of direction and viewpoint, has been perceived as the development direction of next-generation video technologies and has drawn a wide range of researchers' attention. Since FVV images are synthesized via a depth image-based rendering (DIBR) procedure in the "blind" environment (without reference images), a reliable real-time blind quality evaluation and monitoring system is urgently required. But existing assessment metrics do not render human judgments faithfully mainly because geometric distortions are generated by DIBR. To this end, this paper proposes a novel referenceless quality metric of DIBR-synthesized images using the autoregression (AR)-based local image description. It was found that, after the AR prediction, the reconstructed error between a DIBR-synthesized image and its AR-predicted image can accurately capture the geometry distortion. The visual saliency is then leveraged to modify the proposed blind quality metric to a sizable margin. Experiments validate the superiority of our no-reference quality method as compared with prevailing full-, reduced-, and no-reference models.

关键词:

image description Quality assessment depth image-based rendering no-reference autoregression saliency

作者机构:

  • [ 1 ] [Gu, Ke]Beijing Univ Technol, Fac Informat Technol, Beijing Key Lab Computat Intelligence & Intellige, Beijing 100124, Peoples R China
  • [ 2 ] [Qiao, Jun-Fei]Beijing Univ Technol, Fac Informat Technol, Beijing Key Lab Computat Intelligence & Intellige, Beijing 100124, Peoples R China
  • [ 3 ] [Li, Xiaoli]Beijing Univ Technol, Fac Informat Technol, Beijing Key Lab Computat Intelligence & Intellige, Beijing 100124, Peoples R China
  • [ 4 ] [Jakhetiya, Vinit]Bennett Univ, Dept Comp Sci Engn, Greater Noida 201310, India
  • [ 5 ] [Lin, Weisi]Nanyang Technol Univ, Sch Comp Sci & Engn, Singapore 639798, Singapore
  • [ 6 ] [Thalmann, Daniel]Nanyang Technol Univ, Inst Media Innovat, BeingThere Ctr, Singapore 639798, Singapore

通讯作者信息:

  • 顾锞

    [Gu, Ke]Beijing Univ Technol, Fac Informat Technol, Beijing Key Lab Computat Intelligence & Intellige, Beijing 100124, Peoples R China

查看成果更多字段

相关关键词:

相关文章:

来源 :

IEEE TRANSACTIONS ON IMAGE PROCESSING

ISSN: 1057-7149

年份: 2018

期: 1

卷: 27

页码: 394-405

1 0 . 6 0 0

JCR@2022

ESI学科: ENGINEERING;

ESI高被引阀值:156

JCR分区:1

被引次数:

WoS核心集被引频次: 117

SCOPUS被引频次: 128

ESI高被引论文在榜: 6 展开所有

  • 2020-5
  • 2020-3
  • 2020-1
  • 2019-11
  • 2019-9
  • 2018-11

万方被引频次:

中文被引频次:

近30日浏览量: 0

在线人数/总访问数:348/4964742
地址:北京工业大学图书馆(北京市朝阳区平乐园100号 邮编:100124) 联系我们:010-67392185
版权所有:北京工业大学图书馆 站点建设与维护:北京爱琴海乐之技术有限公司