跳到主要导航 跳到搜索 跳到主要内容

Deep Blind Synthesized Image Quality Assessment with Contextual Multi-Level Feature Pooling

  • Xiaochuan Wang
  • , Kai Wang
  • , Bailin Yang
  • , Frederick W.B. Li
  • , Xiaohui Liang*
  • *此作品的通讯作者
  • Beihang University
  • Zhejiang Gongshang University
  • Durham University

科研成果: 书/报告/会议事项章节会议稿件同行评审

摘要

Blind image quality metrics have achieved significant improvement on traditional 2D image dataset, yet still being insufficient for evaluating synthesized images generated from depth-image-based rendering. The geometric distortions in synthesized image are non-uniform, which is challenging for feature representation and pooling. To address this, we propose an end-to-end deep blind synthesized image quality metric SIQA-CFP. We particularly design a contextual multilevel feature pooling module to encode low- and high-level features, which are extracted by a deep pre-trained ResNet. Experimental results on IRCCyN/IVC DIBR dataset show that our method outperforms state-of-the-art synthesized image quality metrics. Our method also achieves competitive performance on traditional 2D image datasets like LIVE Challenge and TID2013.

源语言英语
主期刊名2019 IEEE International Conference on Image Processing, ICIP 2019 - Proceedings
出版商IEEE Computer Society
435-439
页数5
ISBN(电子版)9781538662496
DOI
出版状态已出版 - 9月 2019
活动26th IEEE International Conference on Image Processing, ICIP 2019 - Taipei, 中国台湾
期限: 22 9月 201925 9月 2019

出版系列

姓名Proceedings - International Conference on Image Processing, ICIP
2019-September
ISSN(印刷版)1522-4880

会议

会议26th IEEE International Conference on Image Processing, ICIP 2019
国家/地区中国台湾
Taipei
时期22/09/1925/09/19

指纹

探究 'Deep Blind Synthesized Image Quality Assessment with Contextual Multi-Level Feature Pooling' 的科研主题。它们共同构成独一无二的指纹。

引用此