MS-PCQE: Efficient No-Reference Point Cloud Quality Evaluation via Multi-Scale Interaction Module in Immersive Communications

The evaluation of the quality experience in 3D visual media is increasingly crucial, as user experience plays a pivotal role in the commercial success of immersive displays for widespread 3D graphics. Although numerous methods for assessing the quality of static Point Clouds (PCs) have been proposed, they consistently commence from visual representations of PCs themselves and appear to lack an adequate description of the actual viewing environment for users. In this paper, focal length-oriented point cloud visualization is implemented as a crucial factor for evaluating static PCs with color. The key insight lies in the integration of projection planes with varying focal lengths into the Convolutional Gated Recurrent Unit (ConvGRU) module, enabling the learning of spatial correlation representations across multiple scales to simulate mechanisms of zooming in and zooming out. Then, we propose the dual-branch transformer, incorporating self-attention modeling and information validity-based attention modeling, to improve the efficiency of global feature descriptors in projected images. Finally, the Multi-Layer Perceptron (MLP) is employed to predict quality scores of PCs by aggregating the multi-plane and multi-scale corresponding features along a coarse-to-fine pattern. Towards No-Reference Point Cloud Quality Evaluation (NR-PCQE), the proposed lightweight network, known as MS-PCQE, demonstrates a 3.87%, 0.85%, and 2.10% improvement in SROCC performance compared to the second-ranked approaches in WPC, SJTU-PCQA, and SIAT-PCQD databases respectively, while its inference speed can reach approximately 2 frames per second (fps) without algorithmic acceleration and around 25fps with TensorRT acceleration. All resources can be found at https://github.com/zerosola/MS-PCQE.