A Multi-View Projection and 3D Feature Fusion Model for Full-Reference Point Cloud Quality Assessment

Abstract

Point clouds are widely used to represent 3D visual content in immersive media, digital twins, and autonomous systems, but acquisition, compression, transmission, and rendering can introduce visible geometry and attribute distortions. Full-reference point cloud quality assessment (FR-PCQA) aims to predict the perceptual quality of a distorted point cloud by comparing it with a reference. A reliable FR-PCQA model should consider both the perception of 3D content by the human visual system via projected views and the manifestation of quality degradation in the point cloud geometry, color, and spatial structure. In this paper, we propose a multi-view projection and 3D feature fusion model for FR-PCQA. The proposed model integrates two complementary branches. In the projection branch, DISTS is applied to multi-view renderings aligned with the reference to capture perceptual similarity, and an additional six groups of geometric and photometric fidelity features (e.g., occupancy, depth fidelity and gradient domain fidelity) are developed to describe explicit geometric and photometric differences in the projected observations. In the 3D Feature Fusion branch, PCQM measures local geometry and color degradation, while a global structural descriptor with eight groups covering point count, position, scale, spatial distribution, and density is constructed to characterize the global properties of point clouds. Finally, a gradient boosting regression tree (GBRT) regressor is employed to predict the final quality score. Extensive experimental results show that the Spearman rank order correlation coefficient (SROCC) values are 0.91537, 0.9101, and 0.9778 on the SJTU-PCQA, WPC, and ICIP2020 datasets, respectively, outperforming the existing PCQA methods. These results indicate that the proposed multi-view projection and 3D feature fusion model provides an accurate and interpretable solution for FR-PCQA.