RAVE让3D高斯溅射实现任意速率压缩，无需重训练
RAVE: Rate-Adaptive Visual Encoding for 3D Gaussian Splatting
- 通过可插值的压缩机制，在预设范围间任意调整编码速率
- 在不重训练情况下保持高质量渲染，支持多种设备和带宽环境
- 适合实时沉浸式应用，如VR/AR和流媒体传输
近年来，神经场景表示技术推动了沉浸式多媒体的发展，3D高斯溅射（3DGS）实现了实时逼真的渲染。尽管效率较高，3DGS仍存在内存占用大、训练成本高的问题，促使人们探索压缩方案。现有方法通常采用固定码率，难以适应不同的带宽与设备限制。本文提出一种灵活的3DGS压缩方案，支持在预设边界之间的任意码率插值。该方法计算开销低，任意码率下无需重训练，且在广泛的操作点上均能保持良好渲染质量。实验表明，该方法实现了高效且高质量的压缩，并具备动态码率控制能力，适用于沉浸式应用的实际部署。代码已开源：https://github.com/inspiros/RAVE。
原文摘要 · Abstract (English)
Recent advances in neural scene representations have transformed immersive multimedia, with 3D Gaussian Splatting (3DGS) enabling real-time photorealistic rendering. Despite its efficiency, 3DGS suffers from large memory requirements and costly training procedures, motivating efforts toward compression. Existing approaches, however, operate at fixed rates, limiting adaptability to varying bandwidth and device constraints. In this work, we propose a flexible compression scheme for 3DGS that supports interpolation at any rate between predefined bounds. Our method is computationally lightweight, requires no retraining for any rate, and preserves rendering quality across a broad range of operating points. Experiments demonstrate that the approach achieves efficient, high-quality compression while offering dynamic rate control, making it suitable for practical deployment in immersive applications. The code is available at https://github.com/inspiros/RAVE.
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。