We introduce radiance meshes, a technique for representing radiance fields with constant density tetrahedral cells produced with a Delaunay tetrahedralization. Unlike a Voronoi diagram, a Delaunay tetrahedralization yields simple triangles that are natively supported by existing hardware. As such, our model is able to perform exact and fast volume rendering using both rasterization and ray-tracing. We introduce a new rasterization method that achieves faster rendering speeds than all prior radiance field representations (assuming an equivalent number of primitives and resolution) across a variety of platforms. Optimizing the positions of Delaunay vertices introduces topological discontinuities (edge flips). To solve this, we use a Zip-NeRF-style backbone which allows us to express a smoothly varying field even when the topology changes. Our rendering method exactly evaluates the volume rendering equation and enables high quality, real-time view synthesis on standard consumer hardware. Our tetrahedral meshes also lend themselves to a variety of exciting applications including fisheye lens distortion, physics-based simulation, editing, and mesh extraction.

翻译：我们提出辐射网格技术，这是一种利用Delaunay四面体化生成的恒定密度四面体单元来表示辐射场的方法。与Voronoi图不同，Delaunay四面体化产生的简单三角形结构可直接被现有硬件支持。因此，我们的模型能够通过光栅化和光线追踪实现精确且快速的体绘制。我们提出一种新型光栅化方法，在多种平台上（假设图元数量和分辨率相当）实现了比所有现有辐射场表示更快的渲染速度。优化Delaunay顶点位置会引入拓扑不连续性（边翻转）。为解决此问题，我们采用Zip-NeRF风格的主干网络，即使在拓扑变化时也能表达平滑变化的场。我们的渲染方法精确求解体绘制方程，可在标准消费级硬件上实现高质量实时视图合成。我们的四面体网格还适用于多种创新应用，包括鱼眼镜头畸变、基于物理的仿真、编辑和网格提取。