TreeGCN-ED: Encoding Point Cloud using a Tree-Structured Graph Network
This work addresses the need for efficient point cloud processing in 3D computer vision, though it appears incremental as it builds on existing methods like PointNet and FoldingNet.
The paper tackles the problem of generating robust embeddings for 3D point clouds by proposing a tree-structured autoencoder framework that utilizes hierarchical graph convolution, and it demonstrates applicability in tasks like point cloud completion and single-image 3D reconstruction.
Point cloud is one of the widely used techniques for representing and storing 3D geometric data. In the past several methods have been proposed for processing point clouds. Methods such as PointNet and FoldingNet have shown promising results for tasks like 3D shape classification and segmentation. This work proposes a tree-structured autoencoder framework to generate robust embeddings of point clouds by utilizing hierarchical information using graph convolution. We perform multiple experiments to assess the quality of embeddings generated by the proposed encoder architecture and visualize the t-SNE map to highlight its ability to distinguish between different object classes. We further demonstrate the applicability of the proposed framework in applications like: 3D point cloud completion and Single image-based 3D reconstruction.