Deep probabilistic model for lossless scalable point cloud attribute compression
This work addresses a gap in lossless attribute compression for point clouds, which is important for applications like 3D graphics and virtual reality, though it appears incremental as it builds on existing deep learning techniques.
The paper tackles the problem of lossless scalable point cloud attribute compression by proposing an end-to-end multiscale coding method (MNeT) that projects attributes onto latent spaces for accurate probability modeling, resulting in outperforming recent methods and matching G-PCC version 14 while being substantially faster.
In recent years, several point cloud geometry compression methods that utilize advanced deep learning techniques have been proposed, but there are limited works on attribute compression, especially lossless compression. In this work, we build an end-to-end multiscale point cloud attribute coding method (MNeT) that progressively projects the attributes onto multiscale latent spaces. The multiscale architecture provides an accurate context for the attribute probability modeling and thus minimizes the coding bitrate with a single network prediction. Besides, our method allows scalable coding that lower quality versions can be easily extracted from the losslessly compressed bitstream. We validate our method on a set of point clouds from MVUB and MPEG and show that our method outperforms recently proposed methods and on par with the latest G-PCC version 14. Besides, our coding time is substantially faster than G-PCC.