提升3D高斯点云压缩效率，训练快3倍、解码快5倍。
CAT-3DGS Pro: A New Benchmark for Efficient 3DGS Compression
- 用PCA引导的向量-矩阵超先验替代三平面结构，减少冗余参数。
- 提出交替优化策略，实现46.6%的BD-rate降低，训练提速3倍。
- 适合需要高效压缩与快速解码的3D内容传输与存储场景。
3D高斯点阵（3DGS）在新视角合成方面展现出巨大潜力，但其在传输与存储应用中实现率失真最优压缩仍面临挑战。CAT-3DGS通过上下文自适应三平面超先验实现了端到端优化压缩，达到业界领先性能，但存在训练与解码时间过长的问题。为此，本文提出改进版CAT-3DGS Pro：首先引入基于PCA引导的向量-矩阵超先验，替代原有的三平面超先验以减少冗余参数；其次提出交替优化策略（A-RDO），实现更优的率失真权衡与更快编码；此外，优化了原始采样率策略，显著提升率失真性能。实验表明，在BungeeNeRF上实现46.6%的BD-rate降低和3倍训练速度提升，Amsterdam场景解码速度提升5倍。
原文摘要 · Abstract (English)
3D Gaussian Splatting (3DGS) has shown immense potential for novel view synthesis. However, achieving rate-distortion-optimized compression of 3DGS representations for transmission and/or storage applications remains a challenge. CAT-3DGS introduces a context-adaptive triplane hyperprior for end-to-end optimized compression, delivering state-of-the-art coding performance. Despite this, it requires prolonged training and decoding time. To address these limitations, we propose CAT-3DGS Pro, an enhanced version of CAT-3DGS that improves both compression performance and computational efficiency. First, we introduce a PCA-guided vector-matrix hyperprior, which replaces the triplane-based hyperprior to reduce redundant parameters. To achieve a more balanced rate-distortion trade-off and faster encoding, we propose an alternate optimization strategy (A-RDO). Additionally, we refine the sampling rate optimization method in CAT-3DGS, leading to significant improvements in rate-distortion performance. These enhancements result in a 46.6% BD-rate reduction and 3x speedup in training time on BungeeNeRF, while achieving 5x acceleration in decoding speed for the Amsterdam scene compared to CAT-3DGS.
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。