OceanSplat: Object-aware Gaussian Splatting with Trinocular View Consistency for Underwater Scene Reconstruction
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915738996965376 |
|---|---|
| author | Kweon, Minseong Park, Jinsun |
| author_facet | Kweon, Minseong Park, Jinsun |
| contents | We introduce OceanSplat, a novel 3D Gaussian Splatting-based approach for high-fidelity underwater scene reconstruction. To overcome multi-view inconsistencies caused by scattering media, we design a trinocular setup for each camera pose by rendering from horizontally and vertically translated virtual viewpoints, enforcing view consistency to facilitate spatial optimization of 3D Gaussians. Furthermore, we derive synthetic epipolar depth priors from the virtual viewpoints, which serve as self-supervised depth regularizers to compensate for the limited geometric cues in degraded underwater scenes. We also propose a depth-aware alpha adjustment that modulates the opacity of 3D Gaussians during early training based on their depth along the viewing direction, deterring the formation of medium-induced primitives. Our approach promotes the disentanglement of 3D Gaussians from the scattering medium through effective geometric constraints, enabling accurate representation of scene structure and significantly reducing floating artifacts. Experiments on real-world underwater and simulated scenes demonstrate that OceanSplat substantially outperforms existing methods for both scene reconstruction and restoration in scattering media. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_04984 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | OceanSplat: Object-aware Gaussian Splatting with Trinocular View Consistency for Underwater Scene Reconstruction Kweon, Minseong Park, Jinsun Computer Vision and Pattern Recognition We introduce OceanSplat, a novel 3D Gaussian Splatting-based approach for high-fidelity underwater scene reconstruction. To overcome multi-view inconsistencies caused by scattering media, we design a trinocular setup for each camera pose by rendering from horizontally and vertically translated virtual viewpoints, enforcing view consistency to facilitate spatial optimization of 3D Gaussians. Furthermore, we derive synthetic epipolar depth priors from the virtual viewpoints, which serve as self-supervised depth regularizers to compensate for the limited geometric cues in degraded underwater scenes. We also propose a depth-aware alpha adjustment that modulates the opacity of 3D Gaussians during early training based on their depth along the viewing direction, deterring the formation of medium-induced primitives. Our approach promotes the disentanglement of 3D Gaussians from the scattering medium through effective geometric constraints, enabling accurate representation of scene structure and significantly reducing floating artifacts. Experiments on real-world underwater and simulated scenes demonstrate that OceanSplat substantially outperforms existing methods for both scene reconstruction and restoration in scattering media. |
| title | OceanSplat: Object-aware Gaussian Splatting with Trinocular View Consistency for Underwater Scene Reconstruction |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2601.04984 |