Atlas：面向VR的设备端城市规模3D高斯溅射（3DGS）的算法-硬件协同设计

中文摘要 AI 辅助

3D高斯溅射（3DGS）近来在建筑领域受到广泛关注。然而，在移动VR设备上实现城市规模的3DGS仍具挑战性，因为大规模场景的内存需求远超当前移动GPU的内存容量。本文提出Atlas，一款无需运行时互联网访问即可实现可扩展渲染的设备端城市规模3DGS渲染框架。核心思路是：尽管完整的3DGS模型体量庞大，但在当前位姿和细节层次（LoD）要求下，每帧仅需高斯点的小子集。基于该思路，Atlas引入分层内存卸载机制，仅动态加载必要的高斯数据到设备内存。为进一步提升性能，Atlas提出时序感知的LoD搜索和立体光栅化，以避免VR中的冗余计算。我们还展示了该技术可与现有3DGS加速器集成，硬件开销可忽略不计。总体而言，Atlas相较于GPU基准实现了18.5倍加速，相较于现有最优3DGS加速器实现了3.9倍加速，同时节省了92.4%的能耗。

英文摘要

3D Gaussian splatting (3DGS) has drawn significant attention in the architectural community recently. However, enabling city scale 3DGS on mobile VR devices remains challenging, as the memory requirement of large scale scenes far exceeds the memory capacity of today's mobile GPUs. This paper presents Atlas, an on device city scale 3DGS rendering framework that enables scalable rendering without runtime Internet access. The key insight is that although the full 3DGS model is massive, each frame only requires a small subset of Gaussians under the current pose and level of detail requirement. Based on this insight, Atlas introduces a hierarchical memory offloading mechanism that dynamically loads only necessary Gaussian data into device memory. To further improve performance, Atlas proposes temporal aware LoD search and stereo rasterization to avoid redundant computation in VR. We further show that our technique can be integrated with existing 3DGS accelerators with negligible hardware overhead. Overall, Atlas achieves 18.5x speedup over the GPU baseline and 3.9x speedup over the state of the art 3DGS accelerators, with 92.4% energy savings.

发表机构

• Shanghai Jiao Tong University（上海交通大学）
• IEIT SYSTEMS Co., Ltd.（上海爱意信息科技有限公司）

机构由 AI 辅助整理，请以论文原文为准。