Share Email Print
cover

Proceedings Paper

Rendered virtual view image objective quality assessment
Author(s): Gang Lu; Xiangchun Li; Yi Zhang; Kai Peng
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

The research on rendered virtual view image (RVVI) objective quality assessment is important for integrated imaging system and image quality assessment (IQA). Traditional IQA algorithms cannot be applied directly on the system receiver-side due to interview displacement and the absence of original reference. This study proposed a block-based neighbor reference (NbR) IQA framework for RVVI IQA. Neighbor views used for rendering are employed for quality assessment in the proposed framework. A symphonious factor handling noise and interview displacement is defined and applied to evaluate the contribution of the obtained quality index in each block pair. A three-stage experiment scheme is also presented to testify the proposed framework and evaluate its homogeneity performance when comparing to full reference IQA. Experimental results show the proposed framework is useful in RVVI objective quality assessment at system receiver-side and benchmarking different rendering algorithms.

Paper Details

Date Published: 30 August 2013
PDF: 8 pages
Proc. SPIE 8910, International Symposium on Photoelectronic Detection and Imaging 2013: Imaging Spectrometer Technologies and Applications, 89100F (30 August 2013); doi: 10.1117/12.2032428
Show Author Affiliations
Gang Lu, Huazhong Univ. of Science and Technology (China)
Xiangchun Li, Huazhong Univ. of Science and Technology (China)
Yi Zhang, Huazhong Univ. of Science and Technology (China)
Kai Peng, Huazhong Univ. of Science and Technology (China)


Published in SPIE Proceedings Vol. 8910:
International Symposium on Photoelectronic Detection and Imaging 2013: Imaging Spectrometer Technologies and Applications
Lifu Zhang; Jianfeng Yang, Editor(s)

© SPIE. Terms of Use
Back to Top