English

GLINT: Modeling Scene-Scale Transparency via Gaussian Radiance Transport

Computer Vision and Pattern Recognition 2026-03-30 v1

Abstract

While 3D Gaussian splatting has emerged as a powerful paradigm, it fundamentally fails to model transparency such as glass panels. The core challenge lies in decoupling the intertwined radiance contributions from transparent interfaces and the transmitted geometry observed through the glass. We present GLINT, a framework that models scene-scale transparency through explicit decomposed Gaussian representation. GLINT reconstructs the primary interface and models reflected and transmitted radiance separately, enabling consistent radiance transport. During optimization, GLINT bootstraps transparency localization from geometry-separation cues induced by the decomposition, together with geometry and material priors from a pre-trained video relighting model. Extensive experiments demonstrate consistent improvements over prior methods for reconstructing complex transparent scenes.

Keywords

Cite

@article{arxiv.2603.26181,
  title  = {GLINT: Modeling Scene-Scale Transparency via Gaussian Radiance Transport},
  author = {Youngju Na and Jaeseong Yun and Soohyun Ryu and Hyunsu Kim and Sung-Eui Yoon and Suyong Yeon},
  journal= {arXiv preprint arXiv:2603.26181},
  year   = {2026}
}

Comments

CVPR 2026, Project page: https://youngju-na.github.io/GLINT

R2 v1 2026-07-01T11:40:23.827Z