Ref-DGS: Reflective Dual Gaussian Splatting

TL;DR

Ref-DGS introduces a novel, efficient Gaussian splatting framework that accurately models near-field and far-field reflections without explicit ray tracing, significantly improving reflective scene reconstruction and view synthesis.

Contribution

It proposes a dual Gaussian scene representation and a lightweight adaptive shader to model reflections efficiently, advancing Gaussian splatting methods for reflective scenes.

Findings

Achieves state-of-the-art results on reflective scenes.

Trains faster than ray-based Gaussian methods.

Effectively models near-field and far-field reflections.

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.