GHPT：基于混合路径追踪的实时可重光照高斯泼溅
GHPT: Real-Time Relightable Gaussian Splatting using Hybrid Path Tracing
把高斯泼溅与基于网格的硬件加速路径追踪结合，用 PGSR 重建表面网格与 G-buffer，再做可微逆渲染恢复材质与环境光照，为需要重光照、物体插入合成的 3DGS 场景提供实时可用的分解式表示。
原文依据 we propose Gaussian hybrid path tracing (GHPT), a three-stage framework to acquire relightable Gaussian splatting models
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论三维高斯泼溅（3DGS）已成为高保真三维场景表示的一种有前景的方法。然而，高斯泼溅的重光照与合成仍然具有挑战性，因为路径追踪无法直接应用。现有的高斯泼溅重光照方法通常采用近似渲染公式或依赖高斯光线追踪，导致重光照性能与渲染效率均较低。为解决这些局限，我们提出高斯混合路径追踪（GHPT），一个用于获取可重光照高斯泼溅模型的三阶段框架。第一阶段利用基于平面的高斯泼溅重建表示（PGSR）实现多视图一致的深度渲染，并重建场景的表面网格。第二阶段在所得网格上执行基于物理的可微渲染，以重建材质贴图与环境贴图。第三阶段在 PGSR 渲染得到的 G-buffer 上执行因子化逆路径追踪（FIPT），其中可见性与间接光照通过硬件加速的光线追踪在带有第二阶段重建的材质贴图与环境贴图的网格上进行评估。实验表明，GHPT 的重光照性能优于基线方法，且我们的方法能够对高斯泼溅进行实时的重光照与合成。
英文原文摘要 1392 字符
3D Gaussian splatting (3DGS) has emerged as a promising approach for high-fidelity 3D scene representation. However, relighting and composition of Gaussian splatting remain challenging because path tracing is not directly applicable. Existing relighting methods for Gaussian splatting typically adopt either approximate rendering formulations or rely on Gaussian ray tracing, yielding low relighting performance and low rendering efficiency. To address these limitations, we propose Gaussian hybrid path tracing (GHPT), a three-stage framework to acquire relightable Gaussian splatting models. The first stage utilizes planar-based Gaussian splatting reconstruction representation (PGSR) to enable multi-view consistent depth rendering and reconstruct the surface mesh of a scene. The second stage performs physically-based differentiable rendering on the obtained mesh to reconstruct the material maps and the environment map. The third stage utilizes factorized inverse path tracing (FIPT) on the G-buffer rendered by the PGSR, and visibility and indirect illumination are evaluated by hardware-accelerated ray tracing on the mesh with the material maps and the environment map reconstructed in the second stage. Experiments demonstrate that the relighting performance of GHPT outperforms the baselines, and our method can perform real-time relighting and composition of Gaussian splatting.