GLINT: Modeling Scene-Scale Transparency via Gaussian Radiance Transport
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.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Real-time Image-based Lighting of Glints
Image-based lighting is a widely used technique to reproduce shading under real-world lighting conditions, especially in real-time rendering applications. A particularly challenging scenario involves materials exhibiting…
Glinthawk: A Two-Tiered Architecture for Offline LLM Inference
We introduce Glinthawk, an architecture for offline Large Language Model (LLM) inference. By leveraging a two-tiered structure, Glinthawk optimizes the utilization of the high-end accelerators ("Tier 1") by offloading th…
CPULanguage ModelingLanguage ModellingLarge Language Model3D Gaussian Splatting against Moving Objects for High-Fidelity Street Scene Reconstruction
The accurate reconstruction of dynamic street scenes is critical for applications in autonomous driving, augmented reality, and virtual reality. Traditional methods relying on dense point clouds and triangular meshes str…
3D ReconstructionAutonomous DrivingComputational EfficiencySea-Undistort: A Dataset for Through-Water Image Restoration in High Resolution Airborne Bathymetric Mapping
Accurate image-based bathymetric mapping in shallow waters remains challenging due to the complex optical distortions such as wave induced patterns, scattering and sunglint, introduced by the dynamic water surface, the w…
Image RestorationL3DG: Latent 3D Gaussian Diffusion
We propose L3DG, the first approach for generative 3D modeling of 3D Gaussians through a latent 3D Gaussian diffusion formulation. This enables effective generative 3D modeling, scaling to generation of entire room-scale…
Scene Generation