Neo通过重用更新排序，实现设备端实时3D高斯溅射渲染。
Neo: Real-Time On-Device 3D Gaussian Splatting with Reuse-and-Update Sorting Acceleration
- 利用帧间时间冗余，重用并更新高斯点深度顺序，避免重复排序。
- 相比现有方案，吞吐提升最高达10.0倍，内存带宽减少94.5%。
- 适合移动AR/VR设备，实现实时低延迟高质量3D渲染。
在资源受限设备上实现3D高斯溅射（3DGS）的实时渲染，对提供沉浸式增强现实（AR）和虚拟现实（VR）体验至关重要。然而，现有方案难以在高分辨率下维持高帧率。分析表明，3DGS渲染流程中的排序阶段是主要瓶颈，因其高内存带宽需求。本文提出Neo，引入一种重用与更新排序算法，利用连续帧间高斯点排序的时间冗余性，并设计专用硬件加速器优化该算法。通过高效追踪和更新高斯点深度顺序，而非从头重新排序，显著减少冗余计算与内存带宽压力。实验结果表明，Neo相比最先进的边缘GPU和ASIC解决方案，吞吐量分别提升10.0倍和5.6倍，同时减少DRAM流量94.5%和81.3%。这些改进使高质量、低延迟的设备端3D渲染更具可行性。
原文摘要 · Abstract (English)
3D Gaussian Splatting (3DGS) rendering in real-time on resource-constrained devices is essential for delivering immersive augmented and virtual reality (AR/VR) experiences. However, existing solutions struggle to achieve high frame rates, especially for high-resolution rendering. Our analysis identifies the sorting stage in the 3DGS rendering pipeline as the major bottleneck due to its high memory bandwidth demand. This paper presents Neo, which introduces a reuse-and-update sorting algorithm that exploits temporal redundancy in Gaussian ordering across consecutive frames, and devises a hardware accelerator optimized for this algorithm. By efficiently tracking and updating Gaussian depth ordering instead of re-sorting from scratch, Neo significantly reduces redundant computations and memory bandwidth pressure. Experimental results show that Neo achieves up to 10.0x and 5.6x higher throughput than state-of-the-art edge GPU and ASIC solution, respectively, while reducing DRAM traffic by 94.5% and 81.3%. These improvements make high-quality and low-latency on-device 3D rendering more practical.
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。