Contributions to Lossless Compression of Points Clouds

Symbolic picture for the article. The link opens the image in a large view.
Source: Rafael Cerqueira @

Congratulations to Dat Thanh Nguyen for his journal publication entitled “Lossless Point Cloud Geometry and Attribute Compression Using a Learned Conditional Probability Model“. In recent years, we have witnessed the presence of point cloud data in many aspects of our lives, from immersive media and autonomous driving to healthcare, although at the cost of a tremendous amount of data. A point cloud uses a huge number of 3D points to represent real-world objects and scenes. Each point in the point cloud is characterized by its geometry and attribute information however, most point cloud compression methods handle geometry and attributes independently.

In this work, we present an efficient lossless point cloud compression method that uses sparse tensor-based deep neural networks to learn point cloud geometry and color probability distributions. Our method represents a point cloud with both occupancy feature and three attribute features at different bit depths in a unified representation.

This allows us to efficiently exploit feature-wise and point-wise dependencies within point clouds using a sparse tensor-based neural network, as the color feature and geometry feature are significantly correlated. We thus can build an accurate auto-regressive context model for an arithmetic coder and produce a very low bitrate while providing lossless quality.

Experimental results show that the proposed approach provides a significant gain over compression methods from The Moving Picture Experts Group. Besides, this first learning-based lossless point cloud geometry and attribute compression approach can open up new directions for the application of sparse-based point cloud compression.