Blind Mesh Quality Assessment Method Based on Concave, Convex and Structural Features Analyses

Various visual distortions can inevitably affect 3D mesh model during their transmission and geometrical processing. Therefore, how to evaluate visual quality of 3D mesh becomes an important problem and it is necessary to design effective tools for 3D mesh quality assessment. In this paper, we propose a new blind 3D mesh quality assessment method based on the analysis of concave, convex and structural information. Specifically, the shape index and the curvedness are defined as features to describe the concave and convex information, while the vertex scatter and the distribution of the triangular topology area are defined as features that describe structural information. All the extracted features constitute a final feature vector and the random forest regression is adopted to learn a quality predictor from feature space to quality space. Validation experiments on public database show that the proposed method can accurately predict the quality of 3D mesh.