FlexGaussian：灵活且成本高效的免训练三维高斯泼溅压缩方法
FlexGaussian: Flexible and Cost-Effective Training-Free Compression for 3D Gaussian Splatting
AI总结：
FlexGaussian提出结合混合精度量化与属性判别剪枝的免训练三维高斯压缩方法，无需重训练即可灵活适配多种压缩目标，实现高达96.4%压缩率且PSNR下降小于1dB，速度远超现有方法。
摘要：
三维高斯泼溅已成为表示和渲染复杂三维场景的主流技术，因其高保真度和速度优势而备受青睐。然而，对大规模模型日益增长的需求要求有效的压缩以降低内存和计算成本，尤其是在资源受限的移动和边缘设备上。现有的压缩方法虽然能有效减少三维高斯参数，但往往需要大量的重训练或微调，在变化的压缩约束下缺乏灵活性。本文提出FlexGaussian，一种灵活且成本高效的方法，将混合精度量化与属性判别剪枝相结合，实现免训练的三维高斯压缩。FlexGaussian无需重训练，并能轻松适应多样的压缩目标。评估结果表明，FlexGaussian在保持高渲染质量（PSNR下降小于1 dB）的同时，实现了高达96.4%的压缩率，并可在移动设备上部署。FlexGaussian在数秒内即可实现高压缩比，比最先进的免训练方法快1.7-2.1倍，比涉及训练的方法快10-100倍。代码正在准备中，即将在https://github.com/Supercomputing-System-AI-Lab/FlexGaussian发布。
英文摘要：
3D Gaussian splatting has become a prominent technique for representing and rendering complex 3D scenes, due to its high fidelity and speed advantages. However, the growing demand for large-scale models calls for effective compression to reduce memory and computation costs, especially on mobile and edge devices with limited resources. Existing compression methods effectively reduce 3D Gaussian parameters but often require extensive retraining or fine-tuning, lacking flexibility under varying compression constraints. In this paper, we introduce FlexGaussian, a flexible and cost-effective method that combines mixed-precision quantization with attribute-discriminative pruning for training-free 3D Gaussian compression. FlexGaussian eliminates the need for retraining and adapts easily to diverse compression targets. Evaluation results show that FlexGaussian achieves up to 96.4% compression while maintaining high rendering quality (<1 dB drop in PSNR), and is deployable on mobile devices. FlexGaussian delivers high compression ratios within seconds, being 1.7-2.1x faster than state-of-the-art training-free methods and 10-100x faster than training-involved approaches. The code is being prepared and will be released soon at: https://github.com/Supercomputing-System-AI-Lab/FlexGaussian
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
