Ref-DGS: Reflective Dual Gaussian Splatting

TL;DR

Ref-DGS is presented, a reflective dual Gaussian splatting framework that addresses this trade-off by decoupling surface reconstruction from specular reflection within an efficient rasterization-based pipeline and proposes a lightweight, physically-aware adaptive mixing shader that fuses global and local reflection features.

Abstract

Reflective appearance, especially strong and typically near-field specular reflections, poses a fundamental challenge for accurate surface reconstruction and novel view synthesis. Existing Gaussian splatting methods either fail to model near-field specular reflections or rely on explicit ray tracing at substantial computational cost. We present Ref-DGS, a reflective dual Gaussian splatting framework that addresses this trade-off by decoupling surface reconstruction from specular reflection within an efficient rasterization-based pipeline. Ref-DGS introduces a dual Gaussian scene representation consisting of geometry Gaussians and complementary local reflection Gaussians that capture near-field specular interactions without explicit ray tracing, along with a global environment reflection field for modeling far-field specular reflections. To predict specular radiance, we further propose a lightweight, physically-aware adaptive mixing shader that fuses global and local reflection features. Experiments demonstrate that Ref-DGS achieves state-of-the-art performance on reflective scenes while training substantially faster than ray-based Gaussian methods.

Figures (11)

• Figure 1: An overview of our Ref-DGS framework.
• Figure 2: Left: Input image. Middle: Normal map of the local reflection Gaussians $\mathcal{G}_{\mathrm{local}}$. Right: Illustration of specular reflection, where the surface normal $\mathbf{n}$ is perpendicular to the surface, and the image distance ($\mathrm{id}$) equals the object distance ($\mathrm{od}$).
• Figure 3: Ablation on surface normal estimation. Angular error maps (red: high, blue: low) show that the full model significantly reduces geometric artifacts compared to ablated variants. Chamfer distances (CD) are reported at the bottom.
• Figure 4: Ablation study on the diffuse leakage issue, visualizing the predicted diffuse color.
• Figure 5: Qualitative surface reconstruction results (meshes and normals) on the ShinySynthetic (coffee, toaster) and GlossySynthetic (cat) datasets.