Low-Complexity Patch-based No-Reference Point Cloud Quality Metric exploiting Weighted Structure and Texture Features

TL;DR

PST-PCQA tackles no-reference point cloud quality assessment by decomposing a distorted point cloud into patches and jointly analyzing local structure and texture features. The method uses dual streams (SFE and TFE) with patch-wise weighting and a global aggregation to predict MOS, achieving low model complexity ($1.8$M parameters) and real-time feasibility. Across three large NR PCQA datasets, PST-PCQA yields strong correlations with subjective scores, outperforms many NR baselines, and demonstrates cross-dataset generalization, with ablations confirming the value of patch-wise analysis. The work advances practical quality assessment for point clouds in real-world, reference-unavailable scenarios and suggests avenues for further efficiency gains through adaptive kernels.

Abstract

During the compression, transmission, and rendering of point clouds, various artifacts are introduced, affecting the quality perceived by the end user. However, evaluating the impact of these distortions on the overall quality is a challenging task. This study introduces PST-PCQA, a no-reference point cloud quality metric based on a low-complexity, learning-based framework. It evaluates point cloud quality by analyzing individual patches, integrating local and global features to predict the Mean Opinion Score. In summary, the process involves extracting features from patches, combining them, and using correlation weights to predict the overall quality. This approach allows us to assess point cloud quality without relying on a reference point cloud, making it particularly useful in scenarios where reference data is unavailable. Experimental tests on three state-of-the-art datasets show good prediction capabilities of PST-PCQA, through the analysis of different feature pooling strategies and its ability to generalize across different datasets. The ablation study confirms the benefits of evaluating quality on a patch-by-patch basis. Additionally, PST-PCQA's light-weight structure, with a small number of parameters to learn, makes it well-suited for real-time applications and devices with limited computational capacity. For reproducibility purposes, we made code, model, and pretrained weights available at https://github.com/michaelneri/PST-PCQA.

Figures (6)

• Figure 1: captionDescription of the no-reference point cloud quality assessment task. From acquisition to rendering, the pristine point cloud is subject to several distortions that may impact the quality perceived by the user.
• Figure 2: Examples of compression techniques applied to the House point cloud from WPC Liu_TVCG_2023 dataset: (a) V-PCC with 'geometryQP'= $35$ and 'textureQP'= $45$; (b) Gaussian noise with standard deviation = $0$ for points' coordinates and $16$ for points' RGB values; (c) downsampling uniformly dividing the point cloud in $2^8$ segments; (d) G-PCC with trisoup, 'NodeSizeLog2'= $4$ and RAHT quantization step= $64$.
• Figure 3: Description of the proposed approach.
• Figure 4: SFE and TFE neural architectures.
• Figure 5: SFE and TFE common structure.