TreeGCN-ED: encoding point cloud using a tree-structured graph network

Show simple item record Singh, Prajwal Sadekar, Kaustubh Raman, Shanmuganathan 2021-10-14T13:14:55Z 2021-10-14T13:14:55Z 2021-10
dc.identifier.citation Singh, Prajwal; Sadekar, Kaustubh and Raman, Shanmuganathan, "TreeGCN-ED: encoding point cloud using a tree-structured graph network", arXiv, Cornell University Library, DOI: arXiv:2110.03170v1, Oct. 2021. en_US
dc.description.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.
dc.description.statementofresponsibility by Prajwal Singh, Kaustubh Sadekar and Shanmuganathan Raman
dc.language.iso en_US en_US
dc.publisher Cornell University Library en_US
dc.subject Computer Vision and Pattern Recognition en_US
dc.subject Point cloud en_US
dc.subject TreeGCN-ED en_US
dc.subject Deep learning algorithms en_US
dc.title TreeGCN-ED: encoding point cloud using a tree-structured graph network en_US
dc.type Pre-Print en_US
dc.relation.journal arXiv

Files in this item

Files Size Format View

There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record

Search Digital Repository


My Account