摘要
传统的点云无损编码算法的编码效率较低,基于卷积或自编码器的点云无损编码算法存在一定的特征信息丢失问题。针对以上问题,提出了一种基于可逆神经网络的点云无损编码算法。首先,该算法利用数学上严格可推导的可逆神经网络解决了点云编码过程中的特征信息丢失问题;然后,设计了3D-invertible-block模块,用于提取原始点云的全局信息,确保编码的准确性;最后,设计了上下文占用率预测模块,以约束点云上下文信息,增强网络的非线性表达能力,从而保留完整的原始点云信息。实验结果表明,该算法在MVUB和MPEG 8i数据集上相较于运动图像专家组织(MPEG)提供的基准G-PCC(Geometry-based point cloud compression)表现出更优的编码性能,编码率节省达到了37.25%。
Traditional lossless point cloud encoding algorithms suffer from low encoding efficiency,whereas those based on convolutional and autoencoder networks exhibit a certain degree of feature information loss.To address these issues,the study proposes a lossless point cloud encoding algorithm based on invertible neural networks.First,the proposed algorithm leverages mathematically rigorously deducible invertible neural networks to mitigate the loss of feature information during point cloud encoding.Furthermore,a 3D-invertible-block module is introduced to extract global information from the original point cloud,enhancing the accuracy of encoding.Finally,a context occupancy prediction module is deployed to constrain contextual information from the point cloud,enhancing the network’s nonlinear expression capability and thereby preserving the complete original point cloud information.Experimental results demonstrate that,compared to the benchmark Geometry-based Point Cloud Compression(G-PCC)method provided by the Moving Picture Experts Group(MPEG),the proposed algorithm exhibits superior encoding performance on the MVUB and MPEG 8i datasets,achieving a 37.25%improvement in terms of the encoding rate.
作者
王楷元
方志军
卢俊鑫
Wang Kaiyuan;Fang Zhijun;Lu Junxin(School of Electronic and Electrical Engineering,Shanghai University of Engineering Science,Shanghai 201620,China;School of Computer Science and Technology,East China Normal University,Shanghai 200062,China)
出处
《激光与光电子学进展》
北大核心
2025年第8期167-175,共9页
Laser & Optoelectronics Progress
基金
国家自然科学基金(61831018)。
关键词
激光技术
点云数据
点云无损编码
可逆神经网络
laser technique
point cloud data
lossless point cloud encoding
invertible neural network
作者简介
通信作者:方志军,zjfang@sues.edu.cn。
