A perceptual quality metric for 3D triangle meshes based on spatial pooling

Abstract

In computer graphics, various processing operations are applied on 3D triangle meshes and these processes often involve distortions, which affect the visual quality of surface geometry. In such context, perceptual quality assessment of 3D triangle meshes becomes a crucial issue. In this paper, we propose a new objective quality metric for assessing the visual difference between a reference mesh and a corresponding distorted mesh. Our analysis indicates that the overall quality of a distorted mesh is sensitive to the distortion distribution. The proposed metric is based on a spatial pooling strategy and statistical descriptors of distortion distribution. We generate a perceptual distortion map for vertices in reference mesh while taking into account the visual masking effect of human visual system. The proposed metric extracts statistical descriptors from distortion map as the feature vector to represent the overall mesh quality. With the feature vector as input, we adopt Support Vector Regression model to predict the mesh quality score. We validate the performance of our method with three publicly available databases, and the comparison with state-of-the-art metrics demonstrates the superiority of our method. Experimental results show that our proposed method achieves a high correlation between objective assessment and subjective scores.

Notice of Violation of IEEE Publication Principles: Study on Sports Volleyball Tracking Technology Based on Image Processing and 3D Space Matching

“…Because the features we use to get the similarity are the features of the image, the observation space I k is constructed from discrete time k and the m cameras. As shown in formula (6) below:…”

“…Therefore, in order to obtain more reliable and in-depth tactical analysis in volleyball games, it is very important to obtain more accurate information on volleyball tracks [6]. Therefore, the analysis of the factors affecting the accuracy of volleyball tracking and design a more suitable scheme to solve them, has become the focus of this paper.…”

Comparing surface digitization techniques in palaeontology using visual perceptual metrics and distance computations between 3D meshes

“…2012; Feng et al . 2018). A metric is a function of pairs of images that gives a non‐negative measure of the distance between two images (Lindstrom & Turk 2000).…”

“…2012; Feng et al . 2018) so we relied on perceptual metrics in our study; more specifically, model‐based ones. We computed one of the most used MVQ metrics, the Mesh Structural Distortion Measure 2 (MSDM2) described by Lavoué (2011), which has one of the highest correlation values with MOS.…”

Perceptual Quality Evaluation of 3D Triangle Mesh: A Technical Review

“…On the other hand, the perceptibility of surface contortion relies upon a few elements like lighting conditions and directions, viewpoints, viewing distance (long view distance-low perceptibility of distortions) and surface material. During last ten years, several mesh visual quality (MVQ) metrics are introduced [5], mostly work on structural mapping such as Mesh Structural Distortion Measure (MSDM) [6], MSDM2 [7], Dihedral Angle Mesh Error (DAME) [8], Fast Mesh Perceptual Distance (FMPD) [9], Tensor-based Perceptual Distance Measure (TPDM) [10], Dong [11] and TPDMSP [5]. These are the example of objective quality metrics will probably deliver a score that predicts the subjective visual quality regarding a reference model [2].…”