Octree-GS：基于LOD结构的3D高斯函数的一致实时渲染

Octree-GS: Towards Consistent Real-time Rendering with LOD-Structured 3D Gaussians

March 26, 2024

作者: Kerui Ren, Lihan Jiang, Tao Lu, Mulin Yu, Linning Xu, Zhangkai Ni, Bo Dai

cs.AI

摘要

最近的三维高斯喷洒（3D-GS）相较于基于神经元场景表示的NeRF表现出卓越的渲染保真度和效率。虽然展示了实时渲染的潜力，3D-GS在具有复杂细节的大场景中遇到了渲染瓶颈，这是由于位于视锥体内的高斯基元数量过多所致。这种限制在缩小视图时特别明显，并且可能导致在具有不同细节的场景中渲染速度不一致。此外，它常常难以通过启发式密度控制操作在不同尺度上捕捉相应级别的细节。受到细节级别（LOD）技术的启发，我们引入了Octree-GS，具有LOD结构化的三维高斯方法，支持场景表示的细节级别分解，有助于最终渲染结果。我们的模型动态选择来自多分辨率锚点集的适当级别，确保通过自适应LOD调整保持一致的渲染性能，同时保持高保真度的渲染结果。

English

The recent 3D Gaussian splatting (3D-GS) has shown remarkable rendering fidelity and efficiency compared to NeRF-based neural scene representations. While demonstrating the potential for real-time rendering, 3D-GS encounters rendering bottlenecks in large scenes with complex details due to an excessive number of Gaussian primitives located within the viewing frustum. This limitation is particularly noticeable in zoom-out views and can lead to inconsistent rendering speeds in scenes with varying details. Moreover, it often struggles to capture the corresponding level of details at different scales with its heuristic density control operation. Inspired by the Level-of-Detail (LOD) techniques, we introduce Octree-GS, featuring an LOD-structured 3D Gaussian approach supporting level-of-detail decomposition for scene representation that contributes to the final rendering results. Our model dynamically selects the appropriate level from the set of multi-resolution anchor points, ensuring consistent rendering performance with adaptive LOD adjustments while maintaining high-fidelity rendering results.