TransmissiveGS: Residual-Guided Disentangled Gaussian Splatting for Transmissive Scene Reconstruction and Rendering

2026-05-11

AI Summary

This work addresses the challenge of reconstructing transparent scenes, where near-field reflections and transmitted content are inherently coupled, leading to ambiguities in both geometry and radiance. To resolve this, the authors propose a residual-guided decoupled Gaussian splatting framework that employs dual Gaussian representations to separately model surface and transmission components. The approach integrates a deferred shading function for joint rendering and introduces a reflected light field model combined with high-frequency regularization to enhance detail fidelity. By leveraging multi-view consistency residuals to guide decoupling, the method achieves, for the first time, high-quality joint reconstruction of geometry and appearance in transparent scenes. It significantly outperforms existing Gaussian splatting techniques on both synthetic and real-world data and introduces the first synthetic dataset dedicated to transparent surface reconstruction.

Abstract

Transmissive scenes are ubiquitous in daily life, yet reconstructing and rendering them remains highly challenging due to the inherent entanglement between near-field reflections from the surrounding environment on the transmissive surface, and the transmitted content of the scene behind it. This coupling gives rise to dual surface geometries and dual radiance components within each observation, posing ambiguities for standard methods. We present TransmissiveGS, a novel framework for disentangled reconstruction and rendering of transmissive scenes. Specifically, we model the scene with a dual-Gaussian representation and introduce a deferred shading function to jointly render the two Gaussian components. To separate reflection and transmission, we exploit the inherent multi-view inconsistency of reflections and leverage the residuals from reconstructing multi-view consistent content as cues for disentangled geometry and appearance modeling. We further propose a reflection light field that enables high-fidelity estimation of near-field reflections. During training, we introduce a high-frequency regularization to preserve fine details. We also contribute a new synthetic dataset for evaluating transmissive surface reconstruction. Experiments on both synthetic and real-world scenes demonstrate that TransmissiveGS consistently outperforms prior Gaussian Splatting-based methods in both reconstruction and rendering quality for transmissive scenes.

Problem

• transmissive scenes
• scene reconstruction
• reflection-transmission entanglement
• Gaussian splatting
• multi-view inconsistency

Innovation

• Gaussian Splatting
• transmissive scene
• disentangled rendering
• reflection light field
• multi-view inconsistency