TAFA-GSGC: Group-wise Scalable Point Cloud Geometry Compression with Progressive Residual Refinement

TL;DR

TAFA-GSGC is a scalable point cloud geometry compression method that allows multi-quality decoding from a single bitstream, improving efficiency and quality adaptation.

Contribution

It introduces a novel scalable codec with layered residual refinement and a feature aggregation module, enabling multiple quality levels with better compression performance.

Findings

Supports up to 9 quality levels with monotonic quality improvement.

Achieves average BD-rate reductions of 4.99% and 5.92% in D1-PSNR and D2-PSNR.

Outperforms the PCGCv2 baseline in RD performance.

Abstract

Scalable compression is essential for bandwidth-adaptive transmission, yet most learned codecs are optimized for a fixed rate-distortion point, making rate adaptation costly due to re-encoding or maintaining multiple bitstreams. In this work, we propose TAFA-GSGC, a scalable learned point cloud geometry codec that enables multi-quality decoding from a single bitstream and a single trained model. TAFA-GSGC combines layered residual refinement with channel-group entropy coding, and introduces a Target-Aligned Feature Aggregation module to reduce cross-layer redundancy in enhancement residuals. Our framework supports up to 9 decodable quality levels with monotonic quality improvement as more subbitstreams are received, while maintaining strong compression efficiency. Compared with the PCGCv2 baseline, TAFA-GSGC demonstrates improved RD performance, achieving average BD-rate reductions of 4.99% and 5.92% in terms of D1-PSNR and D2-PSNR, respectively.