MS-ISSM: Objective Quality Assessment of Point Clouds Using Multi-scale Implicit Structural Similarity
This work addresses the problem of objective quality assessment for point clouds, which is crucial for applications like 3D modeling and virtual reality, but it appears incremental as it builds on existing PCQA methods with novel architectural improvements.
The paper tackles the challenge of accurate point cloud quality assessment (PCQA) by proposing MS-ISSM, which uses radial basis functions for implicit structural similarity and a ResGrouped-MLP network to map multi-scale feature differences to perceptual scores, outperforming state-of-the-art metrics in reliability and generalization on multiple benchmarks.
The unstructured and irregular nature of points poses a significant challenge for accurate point cloud quality assessment (PCQA), particularly in establishing accurate perceptual feature correspondence. To tackle this, we propose the Multi-scale Implicit Structural Similarity Measurement (MS-ISSM). Unlike traditional point-to-point matching, MS-ISSM utilizes radial basis function (RBF) to represent local features continuously, transforming distortion measurement into a comparison of implicit function coefficients. This approach effectively circumvents matching errors inherent in irregular data. Additionally, we propose a ResGrouped-MLP quality assessment network, which robustly maps multi-scale feature differences to perceptual scores. The network architecture departs from traditional flat multi-layer perceptron (MLP) by adopting a grouped encoding strategy integrated with residual blocks and channel-wise attention mechanisms. This hierarchical design allows the model to preserve the distinct physical semantics of luma, chroma, and geometry while adaptively focusing on the most salient distortion features across High, Medium, and Low scales. Experimental results on multiple benchmarks demonstrate that MS-ISSM outperforms state-of-the-art metrics in both reliability and generalization. The source code is available at: https://github.com/ZhangChen2022/MS-ISSM.