BQE-CVP: Blind Quality Evaluator for Colored Point Cloud Based on Visual Perception

Abstract

The current researches on 3D point cloud quality evaluation focus on the full reference methods, but the blind quality evaluation has more advantages in actual applications. Therefore, a Blind Quality Evaluator for Colored Point Cloud (CPC) based on Visual Perception (BQE-CVP) is proposed. Firstly, considering the visual masking effect of CPC's geometric information, CPC is segmented into different regions and distributed with different weights to describe the influence of visual masking effect in CPC quality assessment. At the same time, a geometric combination feature vector is defined. Secondly, considering the visual masking effect of CPC's color information, the CPC is projected to the plane and the corresponding visual perception features are extracted. Then, the CPC's color combination feature vector is extracted in the 3D domain to better reflect the color distortion. Thirdly, the joint feature of CPC is extracted as the supplement of the geometric and color features. Finally, all the extracted features are constituted as a feature vector to predict the quality of CPC. Experimental results on three databases (CPCD2.0, IRPC and SJTU-PCQA) show that the proposed metric is better than relevant existing methods.