FilterGS：面向大规模层次细节3D高斯泼溅的无遍历并行过滤与自适应收缩
FilterGS: Traversal-Free Parallel Filtering and Adaptive Shrinking for Large-Scale LoD 3D Gaussian Splatting
FilterGS 提出无需树遍历的并行过滤机制和基于不透明度的自适应高斯收缩策略，可直接用于加速大规模 3DGS 场景的 LoD 渲染，减少冗余高斯-瓦片对的处理开销。
原文依据 parallel filtering mechanism with two complementary filters that enable efficient selection without tree traversal
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论3D高斯泼溅通过实时性能革新了神经渲染。然而，利用层次细节方法将该方法扩展至大场景面临关键挑战：低效的串行遍历消耗超过60%的渲染时间，以及冗余的高斯-瓦片对带来不必要的处理开销。为解决这些局限，我们提出FilterGS，其具备一种并行过滤机制，包含两个互补滤波器，无需树遍历即可实现高效选择，并结合一种场景自适应高斯收缩策略，通过基于不透明度的缩放来最小化冗余。大量实验表明，FilterGS在多个大规模数据集上实现了最优的渲染速度，同时保持有竞争力的视觉质量。
英文原文摘要 802 字符
3D Gaussian Splatting has revolutionized neural rendering with real-time performance. However, scaling this approach to large scenes using Level-of-Detail methods faces critical challenges: inefficient serial traversal consuming over 60% of rendering time, and redundant Gaussian-tile pairs that incur unnecessary processing overhead. To address these limitations, we propose FilterGS, featuring a parallel filtering mechanism with two complementary filters that enable efficient selection without tree traversal, coupled with a scene-adaptive Gaussian shrinkage strategy that minimizes redundancy through opacity-based scaling. Extensive experiments demonstrate that FilterGS achieves state-of-the-art rendering speeds while maintaining competitive visual quality across multiple large-scale datasets.