Perception-Weighted Multi-View Point Cloud Quality Assessment With Saliency-Guided Coverage Analysis

Due to the non-uniform perception of human vision, structural or color changes in salient regions play a dominant role in point cloud quality assessment (PCQA). In this paper, we propose a perception-weighted multi-view PCQA method based on saliency-guided coverage analysis (PW-SCQA), which dynamically quantifies the contribution of different viewpoints on perceptual quality through saliency. First, multi-view projection images are generated based on a polyhedral projection mechanism and multi-scale features are extracted for constructing a 2D saliency map. Then, the 2D to 3D saliency propagation model is used to refine the point-level saliency weights and achieve point cloud saliency visualization. Subsequently, a perception-driven viewpoint optimization mechanism and a novel viewpoint saliency region coverage (SRC) index are innovatively introduced, in which the viewpoint evaluation weights are dynamically adjusted by calculating the SRC of high, medium, and low saliency under the candidate viewpoints. Finally, the multi-view information content weighting image quality assessment method is combined to predict the overall point cloud quality. PW-SCQA outperforms several state-of-the-art methods on three different PCQA datasets.