Point Cloud Geometry Scalable Coding With a Single End-to-End Deep Learning Model

Point clouds are gaining importance as the format to represent complex 3D objects and scenes, offering high user immersion and interaction, although at the cost of requiring massive data. Scalable coding is an important feature for point cloud coding, especially for real-time applications, where the fast and bitrate efficient access to a decoded point cloud is important; however, this issue is still rather unexplored in the literature. With the rise of deep learning methods as a promising solution for efficient coding, this paper proposes the first deep learning-based point cloud geometry scalable coding solution. Experimental results show that the proposed scalable coding solution consistently outperforms the MPEG standard for static point cloud geometry coding. In this way, a new research path is open for point cloud scalable coding technology.

1. Introduction

A point cloud (PC) consists on an unordered set of 3D points, represented by their (x, y, z) coordinates, which are referred to as the geometry. Although this paper focuses on geometry, other attributes may be associated to the points of a PC, notably including colors, normal vectors and reflectance. Since a realistic PC involves a very large number of points, efficient PC compression is a must for transmission and storage to become affordable. However, this type of visual data offers new challenges when compared to traditional image and video, notably the lack of a regular structure and its sparsity, i.e. several more empty voxels than filled. Acknowledging the emerging importance of PC coding, MPEG is in the process of finalizing two PC coding (PCC) standards, known as Geometry based Point Cloud Compression (G-PCC), for static PCs, and Video based Point Cloud Compression (V-PCC), for dynamic PCs [1].