WaterSplatting: Fast Underwater 3D Scene Reconstruction Using Gaussian Splatting

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F25%3A00387805" target="_blank" >RIV/68407700:21230/25:00387805 - isvavai.cz</a>

Nalezeny alternativní kódy

RIV/68407700:21730/25:00387805

Výsledek na webu

<a href="https://doi.org/10.1109/3DV66043.2025.00094" target="_blank" >https://doi.org/10.1109/3DV66043.2025.00094</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/3DV66043.2025.00094" target="_blank" >10.1109/3DV66043.2025.00094</a>

Jazyk výsledku

angličtina

Název v původním jazyce

WaterSplatting: Fast Underwater 3D Scene Reconstruction Using Gaussian Splatting

Popis výsledku v původním jazyce

The underwater 3D scene reconstruction is a challeng ing, yet interesting problem with applications ranging from naval robots to VR experiences. The problem was success fully tackled by fully volumetric NeRF-based methods which can model both the geometry and the medium (water). Un fortunately, these methods are slow to train and do not offer real-time rendering. More recently, 3D Gaussian Splatting (3DGS) method offered a fast alternative to NeRFs. How ever, because it is an explicit method that renders only the geometry, it cannot render the medium and is therefore un suited for underwater reconstruction. Therefore, we pro pose a novel approach that fuses volumetric rendering with 3DGS to handle underwater data effectively. Our method employs 3DGS for explicit geometry representation and a separate volumetric field (queried once per pixel) for cap turing the scattering medium. This dual representation fur ther allows the restoration of the scenes by removing the scattering medium. Our method outperforms state-of-the art NeRF-based methods in rendering quality on the un derwater SeaThru-NeRF dataset. Furthermore, it does so while offering real-time rendering performance, addressing the efficiency limitations of existing methods.

Název v anglickém jazyce

WaterSplatting: Fast Underwater 3D Scene Reconstruction Using Gaussian Splatting

Popis výsledku anglicky

The underwater 3D scene reconstruction is a challeng ing, yet interesting problem with applications ranging from naval robots to VR experiences. The problem was success fully tackled by fully volumetric NeRF-based methods which can model both the geometry and the medium (water). Un fortunately, these methods are slow to train and do not offer real-time rendering. More recently, 3D Gaussian Splatting (3DGS) method offered a fast alternative to NeRFs. How ever, because it is an explicit method that renders only the geometry, it cannot render the medium and is therefore un suited for underwater reconstruction. Therefore, we pro pose a novel approach that fuses volumetric rendering with 3DGS to handle underwater data effectively. Our method employs 3DGS for explicit geometry representation and a separate volumetric field (queried once per pixel) for cap turing the scattering medium. This dual representation fur ther allows the restoration of the scenes by removing the scattering medium. Our method outperforms state-of-the art NeRF-based methods in rendering quality on the un derwater SeaThru-NeRF dataset. Furthermore, it does so while offering real-time rendering performance, addressing the efficiency limitations of existing methods.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

<a href="/cs/project/GX23-07973X" target="_blank" >GX23-07973X: Sjednocená Reprezentace 3D Map</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2025

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

2025 International Conference on 3D Vision (3DV)

ISBN

979-8-3315-3852-1

ISSN

2378-3826

e-ISSN

2475-7888

Počet stran výsledku

10

Strana od-do

969-978

Název nakladatele

IEEE Xplore

Místo vydání

—

Místo konání akce

Singapore

Datum konání akce

25. 3. 2025

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

001572078000085