STQE: Spatial-Temporal Quality Enhancement for G-PCC Compressed Dynamic Point Clouds

2025-07-23

AI Summary

To address the degradation in dynamic point cloud attribute reconstruction quality under Geometry-based Point Cloud Compression (G-PCC), this paper proposes a deep learning–based enhancement framework that jointly exploits spatiotemporal correlations. Methodologically: (i) geometry-motion compensation via recoloring ensures precise inter-frame alignment; (ii) a channel-aware temporal attention mechanism captures long-range temporal dependencies; (iii) a Gaussian-weighted neighborhood aggregation module fuses local geometric and color features; and (iv) a Pearson correlation coefficient–guided joint loss function mitigates over-smoothing artifacts. Evaluated on the G-PCC reference software, the proposed method achieves average PSNR gains of 0.682–0.855 dB for luma and chroma components and reduces BD-rate by 25.2%–32.5% compared to the anchor, significantly outperforming existing attribute enhancement approaches.

Technology Category

• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Computer Vision: Motion & Tracking
• Machine Learning: Learning on the Edge & Model Compression

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Very few studies have addressed quality enhancement for compressed dynamic point clouds. In particular, the effective exploitation of spatial-temporal correlations between point cloud frames remains largely unexplored. Addressing this gap, we propose a spatial-temporal attribute quality enhancement (STQE) network that exploits both spatial and temporal correlations to improve the visual quality of G-PCC compressed dynamic point clouds. Our contributions include a recoloring-based motion compensation module that remaps reference attribute information to the current frame geometry to achieve precise inter-frame geometric alignment, a channel-aware temporal attention module that dynamically highlights relevant regions across bidirectional reference frames, a Gaussian-guided neighborhood feature aggregation module that efficiently captures spatial dependencies between geometry and color attributes, and a joint loss function based on the Pearson correlation coefficient, designed to alleviate over-smoothing effects typical of point-wise mean squared error optimization. When applied to the latest G-PCC test model, STQE achieved improvements of 0.855 dB, 0.682 dB, and 0.828 dB in delta PSNR, with Bjøntegaard Delta rate (BD-rate) reductions of -25.2%, -31.6%, and -32.5% for the Luma, Cb, and Cr components, respectively.

Problem

• Enhancing quality of G-PCC compressed dynamic point clouds
• Exploiting spatial-temporal correlations in point cloud frames
• Addressing over-smoothing in point cloud attribute optimization

Innovation

• Recoloring-based motion compensation for inter-frame alignment
• Channel-aware temporal attention for relevant region highlighting
• Gaussian-guided feature aggregation for spatial dependencies