DGOA:基于动态图和偏移注意力的点云上采样
DGOA:point cloud upsampling based on dynamic graph and offset attention
韩亚振 1尹梦晓 2马伟钊 1杨诗耕 1胡锦飞 1朱丛洋1
作者信息
- 1. 广西大学计算机与电子信息学院,广西 南宁 530004
- 2. 广西大学计算机与电子信息学院,广西 南宁 530004;广西多媒体通信与网络技术重点实验室,广西 南宁 530004
- 折叠
摘要
由三维扫描设备直接得到的点云经常是稀疏、不均匀、有噪声的,因而点云上采样在点云重建、渲染等领域扮演了越来越关键的角色.为此提出了一种新的基于动态图和偏移注意力的点云上采样网络DGOA,主要包含局部特征提取(LFE)、全局特征提取(GFE)和坐标重建(CR)3 个模块.LFE采用多层结构提取邻域信息,每层基于特征相似性构建动态图,可以在特征空间自适应的将点云分组,增大感受野,获得长距离的语义信息,更好的建模点云的局部几何形状.GFE采用基于拉普拉斯算子的偏移注意力使每个点都能获得点云的全局信息,使生成点云的细节与原始点云一致,减少噪声的影响.CR借鉴FoldingNet操作,避免生成点的聚集.此外,整个网络与输入点云中点的顺序无关,具有置换不变性.在多个数据集的定量与定性实验结果表明,该方法优于其他方法,并且具有良好的泛化性和稳定性.
Abstract
The point clouds obtained directly from 3D scanning equipment are often sparse,uneven,and noisy.Therefore,point cloud upsampling has become increasingly vital in fields such as point cloud reconstruction and rendering.A new point cloud upsampling network named DGOA was proposed based on Dynamic Graph and Offset Attention.DGOA mainly consisted of three modules:LFE(local feature extraction),GFE(global feature extraction),and CR(coordinate reconstruction).LFE utilized a multi-layer structure to extract neighborhood information,constructed a dynamic graph based on feature similarity at each layer,and adaptively grouped point clouds in the feature space.This increased the receptive field,obtained long-distance semantic information,and more effectively modeled the local geometry of the point cloud.GFE employed offset attention based on the Laplace operator,enabling each point to obtain global information of the point cloud.This ensured that the details of the generated point cloud were consistent with the original point cloud and reduced the impact of noise.CR,inspired by the FoldingNet operation,prevented the generated points from clustering together.In addition,the entire network was permutation invariant with respect to the order of points in the input point cloud.Quantitative and qualitative experimental results on multiple datasets demonstrated that the proposed method outperformed other methods and exhibited good generalization and stability.
关键词
点云/点云上采样/动态图/偏移注意力/深度学习Key words
point cloud/point cloud upsampling/dynamic graph/offset attention/deep learning引用本文复制引用
出版年
2024
NETL
NSTL
万方数据