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

Wang, Xiaochuan; Wang, Kai; Yang, Bailin; Li, Frederick W.B.; Liang, Xiaohui

doi:10.1109/icip.2019.8802943

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

Wang, Xiaochuan; Wang, Kai; Yang, Bailin; Li, Frederick W.B.; Liang, Xiaohui

Authors

Xiaochuan Wang

Kai Wang

Bailin Yang

Dr Frederick Li frederick.li@durham.ac.uk
Associate Professor

Xiaohui Liang

Abstract

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.

Citation

Wang, X., Wang, K., Yang, B., Li, F. W., & Liang, X. (2019). Deep Blind Synthesized Image Quality Assessment with Contextual Multi-Level Feature Pooling. In 2019 IEEE International Conference on Image Processing Proceedings (435-439). https://doi.org/10.1109/icip.2019.8802943

Conference Name	2019 IEEE International Conference on Image Processing (ICIP)
Conference Location	Taipei, Taiwan
Acceptance Date	Apr 30, 2019
Online Publication Date	Aug 26, 2019
Publication Date	Aug 26, 2019
Deposit Date	Oct 30, 2019
Publicly Available Date	Oct 30, 2019
Pages	435-439
Series ISSN	2381-8549
Book Title	2019 IEEE International Conference on Image Processing Proceedings.
DOI	https://doi.org/10.1109/icip.2019.8802943
Related Public URLs	https://ieeexplore.ieee.org/document/8802943

Files

Accepted Conference Proceeding (824 Kb)
PDF

Copyright Statement
© 2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.