RT-GS: Gaussian Splatting with Reflection and Transmittance Primitives

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Zeng, Kunnong, Peng, Chensheng, Xie, Yichen, Tomizuka, Masayoshi, Yuksel, Cem
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866914436759945216
author Zeng, Kunnong
Peng, Chensheng
Xie, Yichen
Tomizuka, Masayoshi
Yuksel, Cem
author_facet Zeng, Kunnong
Peng, Chensheng
Xie, Yichen
Tomizuka, Masayoshi
Yuksel, Cem
contents Gaussian Splatting is a powerful tool for reconstructing diffuse scenes, but it struggles to simultaneously model specular reflections and the appearance of objects behind semi-transparent surfaces. These specular reflections and transmittance are essential for realistic novel view synthesis, and existing methods do not properly incorporate the underlying physical processes to simulate them. To address this issue, we propose RT-GS, a unified framework that integrates a microfacet material model and ray tracing to jointly model specular reflection and transmittance in Gaussian Splatting. We accomplish this by using separate Gaussian primitives for reflections and transmittance, which allow modeling distant reflections and reconstructing objects behind transparent surfaces concurrently. We utilize a differentiable ray tracing framework to obtain the specular reflection and transmittance appearance. Our experiments demonstrate that our method successfully produces reflections and recovers objects behind transparent surfaces in complex environments, achieving significant qualitative improvements over prior methods where these specular light interactions are prominent.
format Preprint
id arxiv_https___arxiv_org_abs_2604_00509
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle RT-GS: Gaussian Splatting with Reflection and Transmittance Primitives
Zeng, Kunnong
Peng, Chensheng
Xie, Yichen
Tomizuka, Masayoshi
Yuksel, Cem
Graphics
Computer Vision and Pattern Recognition
Gaussian Splatting is a powerful tool for reconstructing diffuse scenes, but it struggles to simultaneously model specular reflections and the appearance of objects behind semi-transparent surfaces. These specular reflections and transmittance are essential for realistic novel view synthesis, and existing methods do not properly incorporate the underlying physical processes to simulate them. To address this issue, we propose RT-GS, a unified framework that integrates a microfacet material model and ray tracing to jointly model specular reflection and transmittance in Gaussian Splatting. We accomplish this by using separate Gaussian primitives for reflections and transmittance, which allow modeling distant reflections and reconstructing objects behind transparent surfaces concurrently. We utilize a differentiable ray tracing framework to obtain the specular reflection and transmittance appearance. Our experiments demonstrate that our method successfully produces reflections and recovers objects behind transparent surfaces in complex environments, achieving significant qualitative improvements over prior methods where these specular light interactions are prominent.
title RT-GS: Gaussian Splatting with Reflection and Transmittance Primitives
topic Graphics
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2604.00509