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

Abstract

Point cloud is an efficient way of representing and storing 3D geometric data. Deep learning algorithms on point clouds are time and memory efficient. Several methods such as PointNet and FoldingNet have been proposed for processing point clouds. This work proposes an autoencoder based framework to generate robust embeddings for 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.

Point Cloud Completion: A Survey

“…We also recommend researchers to use radar scans [25], temporal data [52] etc. Datasets from different real-world environments like aerial scans from drones, 3D scans of living things [80], [201], and subsea data [202], [203] from underwater vehicles could be useful for completion. Specifically, there are no real-world underwater datasets publicly available, indicating a largely unexplored research area.…”

Classifying Objects in 3D Point Clouds Using Recurrent Neural Network: A GRU LSTM Hybrid Approach

“…The network achieved FPD 0.809 and 0.439 on Chair and Airplane, respec-tively. Tree-GAN structures have been used in many other studies, the most important of which are models PT2PC [14], HSGAN [15], TreeGCN-ED [16], and SP-GAN [17] were mentioned.…”

“…Figures 3 and 4 show the effect of choosing different categories and dropouts. The values [8,16,32,64,128,296,512,1024] were considered for the batch size, and [0.2,0.3,0.4,0.5,0.6,0.7,0.8,0.9] for the dropout size. The best results for models with high batch sizes and the worst results in Dropout are obtained for models with low rates.…”