Novel view synthesis has experienced significant advancements owing to increasingly capable NeRF- and 3DGS-based methods. However, reflective object reconstruction remains challenging, lacking a proper solution to achieve real-time, high-quality rendering while accommodating inter-reflection. To fill this gap, we introduce a Reflective Gaussian splatting (\textbf{Ref-Gaussian}) framework characterized with two components: (I) {\em Physically based deferred rendering} that empowers the rendering equation with pixel-level material properties via formulating split-sum approximation; (II) {\em Gaussian-grounded inter-reflection} that realizes the desired inter-reflection function within a Gaussian splatting paradigm for the first time. To enhance geometry modeling, we further introduce material-aware normal propagation and an initial per-Gaussian shading stage, along with 2D Gaussian primitives. Extensive experiments on standard datasets demonstrate that Ref-Gaussian surpasses existing approaches in terms of quantitative metrics, visual quality, and compute efficiency. Further, we show that our method serves as a unified solution for both reflective and non-reflective scenes, going beyond the previous alternatives focusing on only reflective scenes. Also, we illustrate that Ref-Gaussian supports more applications such as relighting and editing.
新视图合成技术因日益强大的 NeRF 和 3DGS 方法而取得了显著进展。然而，对于反射性物体的重建仍然面临挑战，缺乏能够在实现实时高质量渲染的同时处理互反射的解决方案。为填补这一空白，我们提出了一种 Reflective Gaussian Splatting（Ref-Gaussian）框架，该框架由以下两个关键组件构成：1) 基于物理的延迟渲染（Physically based deferred rendering）：通过公式化分割求和近似（split-sum approximation），使渲染方程具备像素级材质属性支持。2) 基于高斯的互反射（Gaussian-grounded inter-reflection）：首次在高斯喷射框架内实现了期望的互反射功能。 为增强几何建模，我们进一步引入了 材质感知法线传播 和 初始高斯着色阶段，并结合 二维高斯基元。 在标准数据集上的大量实验表明，Ref-Gaussian 在定量指标、视觉质量和计算效率方面均优于现有方法。此外，我们证明了该方法不仅能够处理反射场景，还可以统一应用于反射和非反射场景，超越了以往仅聚焦于反射场景的替代方案。同时，我们还展示了 Ref-Gaussian 支持更多应用，如重新光照和编辑。