UGAE: Unified Geometry and Attribute Enhancement for G-PCC Compressed Point Clouds

2025-10-27

AI Summary

To address the joint geometric-attribute distortion in Geometry-based Point Cloud Compression (G-PCC), this paper proposes a unified geometry–attribute co-enhancement framework. Methodologically: (1) a detail-aware K-nearest neighbor (DA-KNN) guided recoloring strategy is designed to balance high-frequency detail preservation and low-frequency fidelity; (2) a Transformer-enhanced sparse convolutional U-Net predicts voxel occupancy; and (3) a residual prediction network with weighted MSE loss optimizes attribute reconstruction. Evaluated on the 8iVFB, Owlii, and MVUB datasets, the method achieves an average 9.98 dB improvement in geometric D1 distortion, a 3.67 dB gain in Y-component PSNR, and reduces bitrates by 90.98% and 56.88%, respectively, compared to baseline G-PCC. These results demonstrate substantial improvements in both objective reconstruction quality and subjective visual perception.

Technology Category

• Data Mining & Knowledge Management: Data Compression
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Computer Vision: Adversarial Attacks & Robustness

Application Category

• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Lossy compression of point clouds reduces storage and transmission costs; however, it inevitably leads to irreversible distortion in geometry structure and attribute information. To address these issues, we propose a unified geometry and attribute enhancement (UGAE) framework, which consists of three core components: post-geometry enhancement (PoGE), pre-attribute enhancement (PAE), and post-attribute enhancement (PoAE). In PoGE, a Transformer-based sparse convolutional U-Net is used to reconstruct the geometry structure with high precision by predicting voxel occupancy probabilities. Building on the refined geometry structure, PAE introduces an innovative enhanced geometry-guided recoloring strategy, which uses a detail-aware K-Nearest Neighbors (DA-KNN) method to achieve accurate recoloring and effectively preserve high-frequency details before attribute compression. Finally, at the decoder side, PoAE uses an attribute residual prediction network with a weighted mean squared error (W-MSE) loss to enhance the quality of high-frequency regions while maintaining the fidelity of low-frequency regions. UGAE significantly outperformed existing methods on three benchmark datasets: 8iVFB, Owlii, and MVUB. Compared to the latest G-PCC test model (TMC13v29), UGAE achieved an average BD-PSNR gain of 9.98 dB and 90.98% BD-bitrate savings for geometry under the D1 metric, as well as a 3.67 dB BD-PSNR improvement with 56.88% BD-bitrate savings for attributes on the Y component. Additionally, it improved perceptual quality significantly.

Problem

• Enhancing geometry structure precision in compressed point clouds
• Improving attribute quality with geometry-guided recoloring strategy
• Reducing distortion in both geometry and attribute compression

Innovation

• Transformer-based U-Net reconstructs geometry via voxel occupancy
• Geometry-guided recoloring preserves details using DA-KNN method
• Attribute residual network enhances quality with W-MSE loss