TreeGCN-ED: Encoding Point Cloud using a Tree-Structured Graph Network

TL;DR

This paper introduces TreeGCN-ED, a tree-structured graph neural network autoencoder that effectively encodes 3D point clouds, capturing hierarchical features for improved shape understanding and applications like completion and reconstruction.

Contribution

It presents a novel hierarchical autoencoder architecture using graph convolution for robust point cloud embeddings, advancing 3D shape analysis techniques.

Findings

Embeddings effectively distinguish object classes in t-SNE visualizations.

Framework improves 3D point cloud completion accuracy.

Demonstrates successful single image-based 3D reconstruction.

Abstract

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.