G-PCC Post-Processing Using Fractional Super-Resolution

TL;DR

This paper introduces a post-processing method for point cloud compression that applies fractional super-resolution to enhance geometric quality after MPEG G-PCC decoding, showing significant improvements over standard decoding.

Contribution

It adapts fractional super-resolution for G-PCC compressed point clouds, providing a simple yet effective enhancement technique that improves quality without requiring extensive retraining.

Findings

Significant quality improvement over standard G-PCC decoding.

Comparable performance to machine-learning-based enhancement methods.

Effective for both solid and non-solid point clouds with minimal additional data.

Abstract

We present a method for post-processing point clouds' geometric information by applying a previously proposed fractional super-resolution technique to clouds compressed and decoded with MPEG's G-PCC codec. In some sense, this is a continuation of that previous work, which requires only a down-scaled point cloud and a scaling factor, both of which are provided by the G-PCC codec. For non-solid point clouds, an a priori down-scaling is required for improved efficiency. The method is compared to the GPCC itself, as well as machine-learning-based techniques. Results show a great improvement in quality over GPCC and comparable performance to the latter techniques, with the