arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.13827cs.CVcs.AR
收藏

使用聚类识别不必要的3D高斯以实现3D高斯泼溅的快速渲染

Identifying Unnecessary 3D Gaussians using Clustering for Fast Rendering of 3D Gaussian Splatting

Joongho Jo, Hyeongwon Kim, Jongsun Park

AI总结:

本文提出一种基于离线聚类的计算减少技术,快速识别并剔除不必要的3D高斯,在保证图像质量下降低渲染开销,并设计了高效GPU硬件架构实现10.7倍加速。

摘要:

3D高斯泼溅(3D-GS)是一种新的渲染方法,在速度和图像质量上均优于神经辐射场(NeRF)。3D-GS利用数百万个3D高斯表示3D场景,并将这些高斯投影到2D图像平面上进行渲染。然而,在渲染过程中,当前视角下存在大量不必要的3D高斯,导致识别它们产生显著的计算开销。本文提出一种计算减少技术,能在实时渲染当前视角时快速识别不必要的3D高斯,且不损害图像质量。该方法通过对距离相近的3D高斯进行离线聚类,随后在运行时将这些聚类投影到2D图像平面上来实现。此外,我们分析了该技术在GPU上执行的瓶颈,并提出一种高效硬件架构,无缝支持该方案。对于Mip-NeRF360数据集,该技术在2D图像投影前平均排除了63%的3D高斯,在不牺牲峰值信噪比(PSNR)的情况下,将整体渲染计算量减少了近38.3%。所提出的加速器相比GPU也实现了10.7倍的加速。

英文摘要:

3D Gaussian splatting (3D-GS) is a new rendering approach that outperforms the neural radiance field (NeRF) in terms of both speed and image quality. 3D-GS represents 3D scenes by utilizing millions of 3D Gaussians and projects these Gaussians onto the 2D image plane for rendering. However, during the rendering process, a substantial number of unnecessary 3D Gaussians exist for the current view direction, resulting in significant computation costs associated with their identification. In this paper, we propose a computational reduction technique that quickly identifies unnecessary 3D Gaussians in real-time for rendering the current view without compromising image quality. This is accomplished through the offline clustering of 3D Gaussians that are close in distance, followed by the projection of these clusters onto a 2D image plane during runtime. Additionally, we analyze the bottleneck associated with the proposed technique when executed on GPUs and propose an efficient hardware architecture that seamlessly supports the proposed scheme. For the Mip-NeRF360 dataset, the proposed technique excludes 63% of 3D Gaussians on average before the 2D image projection, which reduces the overall rendering computation by almost 38.3% without sacrificing peak-signal-to-noise-ratio (PSNR). The proposed accelerator also achieves a speedup of 10.7x compared to a GPU.

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。

↑