MS-ISSM: Objective Quality Assessment of Point Clouds Using Multi-scale Implicit Structural Similarity

2026-01-03

arXiv.org

AI Summary

This work addresses the challenge of perceptual quality assessment for point clouds, whose unstructured nature hinders reliable feature correspondence. To overcome this, the authors propose a multi-scale implicit structural similarity metric that represents local geometry and color features via radial basis functions (RBFs), transforming distortion measurement into a comparison of implicit function coefficients—thereby circumventing errors inherent in traditional point-to-point matching. Furthermore, they introduce a ResGrouped-MLP network that integrates grouped encoding, residual blocks, and channel attention mechanisms to effectively fuse multi-scale luminance, chrominance, and geometric semantic information, emphasizing critical distortion characteristics. Experimental results demonstrate that the proposed method significantly outperforms existing point cloud quality metrics across multiple benchmarks, achieving state-of-the-art performance in both reliability and generalization capability.

Technology Category

• Computer Vision: Multi-modal Vision
• Machine Learning: Calibration & Uncertainty Quantification
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Security and Privacy: Large-scale security measurements
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work

Abstract

The unstructured and irregular nature of point clouds poses a significant challenge for objective 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 Functions (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 MLPs 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.

Problem

• point cloud
• objective quality assessment
• perceptual feature correspondence
• irregular data
• structural similarity

Innovation

• Multi-scale Implicit Structural Similarity
• Radial Basis Functions
• Point Cloud Quality Assessment
• ResGrouped-MLP
• Channel-wise Attention