电子学报2025，Vol.53Issue(8)：2794-2804,11.DOI:10.12263/DZXB.20240914
基于注意力融合多尺度特征的解压缩点云质量增强方法
A Method for Enhancing the Quality of Decompressed Point Clouds Based on Attention-Fused Multi-Scale Features
钟芯 1唐春明 2彭凌西3
作者信息
- 1. 广州大学计算机科学与网络工程学院,广东 广州 510000
- 2. 广州大学数学与信息科学学院,广东 广州 510000
- 3. 广州大学机械与电气工程学院,广东 广州 510000
- 折叠
摘要
Abstract
Geometry-based point cloud compression(G-PCC)can achieve significant point cloud compression effi-ciency,but decompressing point clouds in low bit rate scenarios produces severe geometric compression artifacts and nega-tively affects the overall visual experience.To address this problem,this paper proposes a geometric quality enhancement method for decompressed point clouds based on attentional fusion of multiscale features.Specifically,the method designs a multi-scale input module to perform downsampling operations on the decompressed point cloud to obtain point cloud data at different scales.Then,the multi-scale point clouds are input in parallel into a discrete convolutional network to extract multi-scale feature information from local to global.Finally,a cross-scale attentional feature fusion module is designed in this paper to fuse the multi-scale features to enhance the completeness and accuracy of the features.The experimental re-sults show that the proposed method achieves an average peak signal-to-noise ratio of 67.968 4 dB on the publicly available dataset,which is an improvement of 1.629 4 dB compared to the standard compression algorithm G-PCC,and the subjective and objective experimental results show that the method can further improve the quality of decompressed point clouds.关键词
点云压缩/深度学习/伪影去除/质量增强/多尺度特征/离散卷积Key words
point cloud compression/deep learning/artifact removal/quality enhancement/multi-scale features/sparse convolution分类
信息技术与安全科学引用本文复制引用
钟芯,唐春明,彭凌西..基于注意力融合多尺度特征的解压缩点云质量增强方法[J].电子学报,2025,53(8):2794-2804,11.
