Dynamic Point Cloud Geometry Compression Using Multiscale Inter Conditional Coding

TL;DR

This paper introduces a multiscale inter conditional coding approach for dynamic point cloud geometry compression, significantly improving compression efficiency over existing standards and learning-based methods.

Contribution

It extends the MSR framework to dynamic point clouds using multiscale temporal priors and contextual information for enhanced compression performance.

Findings

78% lossy BD-Rate gain over V-PCC

45% lossless bitrate reduction over G-PCC

Outperforms recent learning-based solutions

Abstract

This work extends the Multiscale Sparse Representation (MSR) framework developed for static Point Cloud Geometry Compression (PCGC) to support the dynamic PCGC through the use of multiscale inter conditional coding. To this end, the reconstruction of the preceding Point Cloud Geometry (PCG) frame is progressively downscaled to generate multiscale temporal priors which are then scale-wise transferred and integrated with lower-scale spatial priors from the same frame to form the contextual information to improve occupancy probability approximation when processing the current PCG frame from one scale to another. Following the Common Test Conditions (CTC) defined in the standardization committee, the proposed method presents State-Of-The-Art (SOTA) compression performance, yielding 78% lossy BD-Rate gain to the latest standard-compliant V-PCC and 45% lossless bitrate reduction to the latest G-PCC. Even for recently-emerged learning-based solutions, our method still shows significant performance gains.