GlassGaussian: Extending 3D Gaussian Splatting for Realistic Imperfections and Glass Materials

Authors:
Open Access
Publisher website
Google Scholar
Abstract
3D scene reconstruction methods have made significant advancements in handling reflections. However, these methods are primarily effective on ideal mirror surfaces, which limits their applicability in real-world scenarios where imperfections or materials such as glass. The inability of current state-of-the-art (SOTA) methods to accurately model these complex reflective surfaces often results in artifacts and a significant drop in rendering quality. This paper introduces a novel extension to 3D Gaussian Splatting techniques by modifying the image fusion equation and incorporating a single-channel Spherical Harmonics representation to measure the reflectance of each Gaussian kernel from different directions. For glass scene renderings, our method shows an approximate 1dB PSNR improvement compared to current SOTA techniques. Comprehensive experiments demonstrate the effectiveness of our approach in various challenging scenarios.
Funding Information
  • Shanghai Frontiers Science Center of Human-centered Artificial Intelligence
  • Core Facility Platform of Computer Science and Communication, School of Information Science and Technology (SIST), ShanghaiTech University

This publication has 40 references indexed in Scilit: