What question did this study set out to answer?

This research aims to improve the quality of point clouds after lossy compression by enhancing geometry and attributes.

January 24, 2026

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

Key Points

This research aims to improve the quality of point clouds after lossy compression by enhancing geometry and attributes.
Developed a unified geometry and attribute enhancement framework (UGAE).
Implemented post-geometry enhancement using a Transformer-based sparse convolutional U-Net.
Introduced detail-aware K-Nearest Neighbors for geometry-guided recoloring before attribute compression.
Utilized an attribute residual prediction network with weighted mean squared error to enhance attribute quality.
Achieved an average BD-PSNR gain of 9.98 dB and -90.54% BD-bitrate for geometry.
Obtained a 3.34 dB BD-PSNR improvement with -55.53% BD-bitrate for attributes.
Demonstrated significant perceptual quality improvements over existing methods.

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), in terms of total bitrate setting, UGAE achieved an average BD-PSNR gain of 9.98 dB and -90.54% BD-bitrate for geometry under the D1 metric, as well as a 3.34 dB BD-PSNR improvement with -55.53% BD-bitrate for attributes. Additionally, it improved perceptual quality significantly. Our source code will be released on GitHub at: https://github.com/yuanhui0325/UGAE.

AIに質問

Bookmark