Seele：面向移动设备实时高斯泼溅的统一加速框架
Seele: A Unified Acceleration Framework for Real-Time Gaussian Splatting on Mobile Devices
面向移动端 3DGS 的加速框架：通过视图相关场景表示加在线过滤的混合预处理减少无关高斯数量，并在光栅化阶段按贡献度优先调度高斯，可直接嵌入现有 3DGS 管线，为在资源受限设备上部署实时新视角合成提供可复用手段。
原文依据 we propose two GPU-oriented techniques: hybrid preprocessing and contribution-aware rasterization
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（3DGS）已成为许多实时应用的关键渲染技术。然而，当今移动平台有限的硬件资源阻碍了这些应用，使其难以达到实时性能。本文提出 SEELE，一个通用框架，旨在为资源受限的移动设备加速 3DGS 管线。具体而言，我们提出两项面向 GPU 的技术：混合预处理与贡献感知光栅化。混合预处理通过在渲染过程中减少无关高斯的数量，缓解 GPU 的计算与内存压力；其关键在于将我们提出的视图相关场景表示与在线过滤相结合。与此同时，贡献感知光栅化通过优先处理高贡献高斯、减少低贡献高斯的计算，提升光栅化阶段的 GPU 利用率。这两项技术均可在极少微调的情况下无缝集成到现有 3DGS 管线中。总体而言，我们的框架相较现有方法实现了最高 6.3 倍的加速与 39.1% 的模型缩减，同时取得更优的渲染质量。代码将在论文发表后公开。
英文原文摘要 1228 字符
3D Gaussian Splatting (3DGS) has become a crucial rendering technique for many real-time applications. How- ever, the limited hardware resources on today's mobile platforms hinder these applications, as they struggle to achieve real-time performance. In this paper, we propose SEELE, a general framework designed to accelerate the 3DGS pipeline for resource-constrained mobile devices. Specifically, we propose two GPU-oriented techniques: hybrid preprocessing and contribution-aware rasterization. Hybrid preprocessing alleviates the GPU compute and memory pressure by reducing the number of irrelevant Gaussians during rendering. The key is to combine our view-dependent scene representation with online filtering. Meanwhile, contribution-aware rasterization improves the GPU utilization at the rasterization stage by prioritizing Gaussians with high contributions while reducing computations for those with low contributions. Both techniques can be seamlessly integrated into existing 3DGS pipelines with minimal fine-tuning. Collectively, our framework achieves up to 6.3x speedup and 39.1% model reduction while achieving superior rendering quality compared to existing methods. Our codes will be released upon publication.