基于邻域信息和注意力的无参考点云质量评估  

No-reference point cloud quality assessment based on neighbor information and attention

作　　者：陈晓雷[1,2,3] 张育儒 胡森涌 杜泽龙 Chen Xiaolei;Zhang Yuru;Hu Senyong;Du Zelong(School of Electrical Engineering and Information Engineering,Lanzhou University of Technology,Lanzhou 730050,China;Gansu Provincial Key Laboratory of Advanced Control for Industrial Processes,Lanzhou University of Technology,Lanzhou 730050,China;National Experimental Teaching Demonstration Center of Electrical and Control Engineering,Lanzhou University of Technology,Lanzhou 730050,China)

机构地区：[1]兰州理工大学电气工程与信息工程学院,兰州730050 [2]兰州理工大学甘肃省工业过程先进控制重点实验室,兰州730050 [3]兰州理工大学电气与控制工程国家级实验教学示范中心,兰州730050

出　　处：《中国图象图形学报》2024年第10期2979-2991,共13页Journal of Image and Graphics

基　　金：国家自然科学基金项目(61967012)。

摘　　要：目的针对现有无参考点云质量评估方法需要将点云预处理为二维投影或其他形式导致引入额外噪声、限制空间上下文等问题,提出了一种基于邻域信息嵌入变换模块和点云级联注意力模块的无参考点云质量评估方法。方法将点云样本整体作为输入,减轻预处理引入的失真。使用稀疏卷积搭建U型主干网络提取多尺度特征,邻域信息嵌入变换模块逐点学习提取特征,点云级联注意力模块增强小尺度特征,提高特征信息的可辨识性,最后逐步聚合多尺度特征信息形成特征向量,经全局自适应池化和回归函数进行回归预测,得到失真点云质量分数。结果实验在2个数据集上与现有的12种代表性点云质量评估方法进行了比较,在SJTU-PCQA(Shanghai Jiao Tong University subjective point cloud quality assessment)数据集中,相比于性能第2的模型,PLCC(Pearson linear correlation coefficient)值提高了8.7%,SROCC(Spearman rank-order coefficient correlation)值提高了0.39%;在WPC(waterloo point cloud)数据集中,相比于性能第2的模型,PLCC值提高了4.9%,SROCC值提高了3.0%。结论所提出的基于邻域信息嵌入变换和级联注意力的无参考点云质量评估方法,提高了可辨识特征提取能力,使点云质量评估结果更加准确。Objective This study introduces a novel method that aims to address the shortcomings of current no-reference point cloud quality assessment methods.Such methods necessitate the preprocessing of point clouds into 2D projections or other forms,which may introduce additional noise and limit the spatial contextual information of the data.The proposed approach overcomes these limitations.The approach comprises two crucial components,namely,the neighborhood information embedding transformation module and the point cloud cascading attention module.The former module is intended to capture the point cloud data’s local features and geometric structure without any extra preprocessing.This process pre serves the point cloud’s original information and minimizes the potential for introducing additional noise,all while providing a more expansive spatial context.The latter module enhances the precision and flexibility of point cloud quality assessment by merging spatial and channel attention.The module dynamically learns weightings and applies them to features based on the aspects of various point cloud data,resulting in a more comprehensive understanding of multidimensional point cloud information.Method The proposed model employs innovative strategies to address challenges in assessing point cloud quality.In contrast to traditional approaches,it takes the original point cloud sample as input and eliminates the need for preprocessing.This process helps maintain the point cloud’s integrity and improve accuracy in assessment.Second,a U-shaped backbone network is constructed using sparse convolution to enable multiscale feature extraction,allowing the model to capture different scale features of the point cloud and understand point cloud data at local and overall levels more effectively.The module for transforming neighborhood information embedding is an essential part of the process because it extracts features through point-by-point learning.This process assists the model in thoroughly comprehending the local information p

关 键 词：三维质量评估 点云 无参考 邻域信息 级联注意力 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]