In recent years, point clouds have become increasingly popular for representing three-dimensional (3D) visual objects and scenes. To efficiently store and transmit point clouds, compression methods have been developed, but they often result in a degradation of quality. To reduce color distortion in point clouds, we propose a graph-based quality enhancement network (GQE-Net) that uses geometry information as an auxiliary input and graph convolution blocks to extract local features efficiently. Specifically, we use a parallel-serial graph attention module with a multi-head graph attention mechanism to focus on important points or features and help them fuse together. Additionally, we design a feature refinement module that takes into account the normals and geometry distance between points. To work within the limitations of GPU memory capacity, the distorted point cloud is divided into overlap-allowed 3D patches, which are sent to GQE-Net for quality enhancement. To account for differences in data distribution among different color components, three models are trained for the three color components. Experimental results show that our method achieves state-of-the-art performance. For example, when implementing GQE-Net on a recent test model of the geometry-based point cloud compression (G-PCC) standard, 0.43 dB, 0.25 dB, and 0.36 dB Bjontegaard delta (BD)-peak-signal-to-noise ratio (PSNR), corresponding to 14.0%, 9.3%, and 14.5% BD-rate savings can be achieved on dense point clouds for the Y, Cb, and Cr components, respectively. The source code of our method is available at https://github.com/xjr998/GQE-Net.

翻译：近年来，点云在表示三维视觉对象和场景方面日益流行。为高效存储和传输点云，人们开发了多种压缩方法，但这些方法往往导致质量下降。为减少点云颜色失真，我们提出一种基于图的质量增强网络（GQE-Net），该网络利用几何信息作为辅助输入，并通过图卷积模块高效提取局部特征。具体而言，我们采用了一种串并联图注意力模块，结合多头图注意力机制，聚焦于重要点或特征，并促进其融合。此外，我们设计了一个特征细化模块，该模块考虑了点的法向量和几何距离。为适应GPU内存容量的限制，将失真点云划分为允许重叠的三维块，并将其送入GQE-Net进行质量增强。考虑到不同颜色分量间数据分布的差异，我们为三个颜色分量分别训练了三个模型。实验结果表明，我们的方法达到了最先进的性能。例如，将GQE-Net应用于基于几何的点云压缩（G-PCC）标准的最新测试模型时，对于稠密点云，在Y、Cb和Cr分量上分别实现了0.43 dB、0.25 dB和0.36 dB的Bjontegaard delta（BD）峰值信噪比（PSNR）提升，对应14.0%、9.3%和14.5%的BD率节省。本方法的源代码已开源至https://github.com/xjr998/GQE-Net。