基于Transformer的点云几何有损压缩方法  

Lossy point cloud geometry compression based on Transformer

作　　者：刘舸昕 章骏腾 丁丹丹[1] LIU Gexin;ZHANG Junteng;DING Dandan(School of Information Science and Technology,Hangzhou Normal University,Hangzhou 311121,China)

机构地区：[1]杭州师范大学信息科学与技术学院,杭州311121

出　　处：《北京航空航天大学学报》2024年第2期634-642,共9页Journal of Beijing University of Aeronautics and Astronautics

基　　金：国家自然科学基金(6217010731);浙江省自然基金(LY20F010013)。

摘　　要：点云被广泛地用于三维物体表达,不过真实世界采集到的点云往往数据庞大,不利于传输与储存,针对点云数据冗余性问题,引入基于注意力机制的Transformer模块,提出一种基于Transformer的端到端多尺度点云几何压缩方法。将点云进行体素化,在编码端利用稀疏卷积提取特征,进行多尺度的逐步下采样,结合Transformer模块加强点空间特征感知与提取;在解码端进行对应的多尺度上采样重建,同样采用Transformer模块对有用特征进行加强与恢复,逐步细化并重建点云。与2种点云标准编码方法对比,所提方法平均获得80%和75%的BD-Rate增益;与基于深度学习的点云压缩方法对比,平均获得16%的BD-Rate增益,在相同码率点有约0.6的PSNR提升。实验结果表明:Transformer在点云压缩领域的可行性与有效性;在主观质量方面,所提方法也有明显的主观效果提升,重建的点云更接近原始点云。Point clouds are widely used for 3D object representation,however,real-world captured point clouds often have huge data,which is unfavorable for transmission and storage.To address the redundancy problem of point cloud data,an end-to-end Transformer-based multiscale point cloud geometry compression method is proposed by introducing the Transformer module based on the attention mechanism.The point cloud is voxelized,features are extracted using sparse convolution at the encoder,multi-scale gradual downsampling is performed,and the Transformer module is combined to enhance the point-space feature perception and extraction;at the decoder,the corresponding multi-scale up-sampling is performed for reconstruction,and the Transformer module is also used to enhance and recover the useful features,and the point cloud is progressively refined and reconstructed.Compared with two standard point cloud coding methods,the proposed method obtains 80%and 75%BD-Rate gain on average;compared with the deep learning-based point cloud compression method,it obtains 16%BD-Rate gain on average,and there is about 0.6 PSNR enhancement at the same bit rate.The experimental results demonstrate the feasibility and effectiveness of Transformer in the field of point cloud compression.In terms of subjective quality,the proposed method also has significant subjective effect improvement,and the reconstructed point cloud is closer to the original point cloud.

关 键 词：点云几何压缩 TRANSFORMER 注意力机制 深度学习 稀疏卷积 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]