Particle-based representations of radiance fields such as 3D Gaussian Splatting have found great success for reconstructing and re-rendering of complex scenes. Most existing methods render particles via rasterization, projecting them to screen space tiles for processing in a sorted order. This work instead considers ray tracing the particles, building a bounding volume hierarchy and casting a ray for each pixel using high-performance GPU ray tracing hardware. To efficiently handle large numbers of semi-transparent particles, we describe a specialized rendering algorithm which encapsulates particles with bounding meshes to leverage fast ray-triangle intersections, and shades batches of intersections in depth-order. The benefits of ray tracing are well-known in computer graphics: processing incoherent rays for secondary lighting effects such as shadows and reflections, rendering from highly-distorted cameras common in robotics, stochastically sampling rays, and more. With our renderer, this flexibility comes at little cost compared to rasterization. Experiments demonstrate the speed and accuracy of our approach, as well as several applications in computer graphics and vision. We further propose related improvements to the basic Gaussian representation, including a simple use of generalized kernel functions which significantly reduces particle hit counts.

中文翻译：

---

3D 高斯光线追踪：粒子场景的快速追踪


基于粒子的辐射场表示（如 3D 高斯飞溅）在重建和重新渲染复杂场景方面取得了巨大成功。大多数现有方法通过栅格化来渲染粒子，将它们投影到屏幕空间图块上，以便按排序顺序进行处理。相反，这项工作考虑了粒子的光线追踪，构建了边界体积层次结构，并使用高性能 GPU 光线追踪硬件为每个像素投射了一条光线。为了有效地处理大量半透明粒子，我们描述了一种专门的渲染算法，该算法使用边界网格封装粒子以利用快速射线-三角形交集，并按深度顺序对交集进行着色。光线追踪的优势在计算机图形学中是众所周知的：处理非相干光线以获得辅助照明效果（如阴影和反射）、从机器人技术中常见的高度失真相机进行渲染、随机采样光线等。与我们的渲染器相比，使用我们的渲染器时，这种灵活性的成本很小。实验证明了我们方法的速度和准确性，以及计算机图形学和视觉中的多种应用。我们进一步提出了对基本高斯表示的相关改进，包括简单地使用广义核函数，这大大减少了粒子命中次数。