PCGen: A Fully Parallelizable Point Cloud Generative Model

Generative models have the potential to revolutionize 3D extended reality. A primary obstacle is that augmented and virtual reality need real-time computing. Current state-of-the-art point cloud random generation methods are not fast enough for these applications. We introduce a vector-quantized var...

Full description

Bibliographic Details

Published in:	Sensors (Basel, Switzerland) Vol. 24; no. 5; p. 1414
Main Authors:	Vercheval, Nicolas, Royen, Remco, Munteanu, Adrian, Pižurica, Aleksandra
Format:	Journal Article
Language:	English
Published:	Switzerland MDPI AG 22.02.2024 MDPI
Subjects:	autoencoder Euclidean space Machine learning point clouds real-time computing Semantics variational autoencoder vector-quantized variational autoencoder Virtual reality point clouds autoencoder real-time computing variational autoencoder vector-quantized variational autoencoder
ISSN:	1424-8220, 1424-8220
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!