Rendered virtual view image objective quality assessment
Lists
Only you see this
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.
BibTeX
@inproceedings{lu2013rendered,
author = {Gang Lü and Xiangchun Li and Yi Zhang and Kai Peng},
title = {{Rendered virtual view image objective quality assessment}},
booktitle = {Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE},
year = {2013},
doi = {10.1117/12.2032428},
}Loading related content...