Lossless Point Cloud Geometry and Attribute Compression Using a Learned Conditional Probability Model

• Published in: IEEE transactions on circuits and systems for video technology Vol. 33; no. 8; pp. 4337 - 4348
• Main Authors: Nguyen, Dat Thanh, Kaup, Andre
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.08.2023; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Artificial neural networks; Autoregressive models; CNeT; Color; Conditional probability; Context modeling; deep learning; G-PCC; generative probability model; Geometry; Image coding; Machine learning; Mathematical analysis; Neural networks; Octrees; Point cloud attribute coding; Point cloud compression; sparse convolution; Tensors; Three-dimensional displays; Transforms

In recent years, we have witnessed the presence of point cloud data in many aspects of our life, from immersive media, autonomous driving to healthcare, although at the cost of a tremendous amount of data. In this paper, we present an efficient lossless point cloud compression method that uses spars...