Octree-GS：朝向具有LOD結構的3D高斯函數的一致實時渲染

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3D高斯飛濺（3D-GS）相較於基於NeRF的神經場景表示，展現出卓越的渲染保真度和效率。儘管展示了實時渲染的潛力，3D-GS在具有複雜細節的大場景中遇到渲染瓶頸，這是由於位於視錐體內的高斯基元過多所致。這種限制在縮小視圖時尤為明顯，可能導致在細節變化的場景中出現渲染速度不一致的情況。此外，它常常難以通過啟發式密度控制操作在不同尺度上捕捉相應細節水平。受到層級細節（LOD）技術的啟發，我們引入了Octree-GS，採用LOD結構化的3D高斯方法，支持場景表示的層級細節分解，有助於最終渲染結果。我們的模型從多分辨率錨點集中動態選擇適當層級，確保具有自適應LOD調整的一致渲染性能，同時保持高保真度的渲染結果。

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.