Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2603.26181 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915894836330496 |
|---|---|
| author | Na, Youngju Yun, Jaeseong Ryu, Soohyun Kim, Hyunsu Yoon, Sung-Eui Yeon, Suyong |
| author_facet | Na, Youngju Yun, Jaeseong Ryu, Soohyun Kim, Hyunsu Yoon, Sung-Eui Yeon, Suyong |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_26181 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | GLINT: Modeling Scene-Scale Transparency via Gaussian Radiance Transport Na, Youngju Yun, Jaeseong Ryu, Soohyun Kim, Hyunsu Yoon, Sung-Eui Yeon, Suyong Computer Vision and Pattern Recognition 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. |
| title | GLINT: Modeling Scene-Scale Transparency via Gaussian Radiance Transport |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.26181 |