Structure-Aware Graph Convolution Network for Point Cloud Parsing

doi:10.1109/TMM.2022.3216951

Structure-Aware Graph Convolution Network for Point Cloud Parsing

2023-01-01

7

PRE

AI

DOI：10.1109/TMM.2022.3216951

Original

Original request for help

Save

Abstract

En 中文

Point clouds are becoming a popular medium to describe 3D scenes, benefitting from their accuracy and completeness in expressing the spatial and geometrical information of objects. However, due to the disorder and uneven distribution nature, merely selecting neighbors for point clouds in Euclidean space is inefficient and position-ignoring. To fill this gap, we propose a structure-aware graph convolution network (SA-GCN), which consists of an adaptive dilated KNN module (ADKNN), a learnable graph filter (LGF), and a structure-aware feature transformation module (SFT). Specially, the ADKNN module can dynamically adjust the range of grouping neighbor points, while being universal to improve the performance of arbitrary KNN-based methods. Moreover, with the localized auxiliary information provided by LGF, our SFT module disentangles the spatial details as a sort of coding guidance for better deep feature representations. Extensive experimental results on point cloud classification and segmentation tasks demonstrate the superiority of our proposed network.

Keywords:

Point cloud compression

Convolution

Task analysis

Kernel

Three-dimensional displays

Feature extraction

Decoding

Point cloud parsing

adaptive neighbor selection

shape message passing

feature-wise transformation

Structure-Aware Graph Convolution Network for Point Cloud Parsing

Abstract

Journal

Organization