PROJECT TITLE :
NIQSV+ A No-Reference Synthesized View Quality Assessment Metric - 2018
Benefiting from multi-read video and depth and depth-image-based mostly-rendering technologies, only limited views of a real 3-D scene need to be captured, compressed, and transmitted. But, the standard assessment of synthesized views is terribly challenging, since some new varieties of distortions, which are inherently different from the texture coding errors, are inevitably produced by view synthesis and depth map compression, and also the corresponding original views (reference views) are typically not on the market. Thus the full-reference quality metrics cannot be used for synthesized views. During this Project, we have a tendency to propose a novel no-reference image quality assessment technique for three-D synthesized views (called NIQSV+). This blind metric can evaluate the quality of synthesized views by measuring the typical synthesis distortions: blurry regions, black holes, and stretching, with access to neither the reference image nor the depth map. To judge the performance of the proposed method, we have a tendency to compare it with four full-reference 3-D (synthesized read dedicated) metrics, 5 full-reference a pair of-D metrics, and 3 no-reference two-D metrics. In terms of their correlations with subjective scores, our experimental results show that the proposed no-reference metric approaches the most effective of the state-of-the-art full reference and no-reference three-D metrics; and outperforms the widely used no-reference and full-reference two-D metrics significantly. In terms of its approximation of human ranking, the proposed metric achieves the best performance in the experimental check.
Did you like this research project?
To get this research project Guidelines, Training and Code... Click Here