Variable Rate Compression for Raw 3D Point Clouds
This addresses the need for efficient and flexible compression of 3D point clouds in applications like autonomous driving and virtual reality, offering a novel approach that is not incremental but directly improves upon existing methods.
The paper tackles the problem of compressing raw 3D point clouds by proposing a variable rate deep compression architecture that avoids downsampling or voxelization, achieving state-of-the-art results with computational efficiency and no loss of information.
In this paper, we propose a novel variable rate deep compression architecture that operates on raw 3D point cloud data. The majority of learning-based point cloud compression methods work on a downsampled representation of the data. Moreover, many existing techniques require training multiple networks for different compression rates to generate consolidated point clouds of varying quality. In contrast, our network is capable of explicitly processing point clouds and generating a compressed description at a comprehensive range of bitrates. Furthermore, our approach ensures that there is no loss of information as a result of the voxelization process and the density of the point cloud does not affect the encoder/decoder performance. An extensive experimental evaluation shows that our model obtains state-of-the-art results, it is computationally efficient, and it can work directly with point cloud data thus avoiding an expensive voxelized representation.