单模型实现点云几何多质量解码，支持9级渐进质量提升。
TAFA-GSGC: Group-wise Scalable Point Cloud Geometry Compression with Progressive Residual Refinement
- 分层残差精炼+通道组熵编码，实现单一码流多质量解码。
- 相比PCGCv2，D1和D2-PSNR下平均码率降低4.99%和5.92%。
- 适合需要自适应带宽传输的点云应用，如3D地图、虚拟现实。
可扩展压缩对自适应带宽传输至关重要，但多数学习型编码器仅针对固定率-失真点优化，导致速率适配需重新编码或维护多个码流。本文提出TAFA-GSGC，一种可扩展的点云几何学习编码器，支持从单一码流和单个训练模型中实现多质量解码。该方法结合分层残差精炼与通道组熵编码，并引入目标对齐特征聚合模块，降低增强残差中的跨层冗余。框架支持最多9个可解码质量层级，接收更多子码流时质量单调提升，同时保持高效压缩性能。相较于基准方法PCGCv2，TAFA-GSGC在D1-PSNR和D2-PSNR上分别实现平均4.99%和5.92%的BD-rate降低。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。