Gaussian Splashing: Direct Volumetric Rendering Underwater

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Mualem, Nir, Amoyal, Roy, Freifeld, Oren, Akkaynak, Derya
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917053935386624
author Mualem, Nir
Amoyal, Roy
Freifeld, Oren
Akkaynak, Derya
author_facet Mualem, Nir
Amoyal, Roy
Freifeld, Oren
Akkaynak, Derya
contents In underwater images, most useful features are occluded by water. The extent of the occlusion depends on imaging geometry and can vary even across a sequence of burst images. As a result, 3D reconstruction methods robust on in-air scenes, like Neural Radiance Field methods (NeRFs) or 3D Gaussian Splatting (3DGS), fail on underwater scenes. While a recent underwater adaptation of NeRFs achieved state-of-the-art results, it is impractically slow: reconstruction takes hours and its rendering rate, in frames per second (FPS), is less than 1. Here, we present a new method that takes only a few minutes for reconstruction and renders novel underwater scenes at 140 FPS. Named Gaussian Splashing, our method unifies the strengths and speed of 3DGS with an image formation model for capturing scattering, introducing innovations in the rendering and depth estimation procedures and in the 3DGS loss function. Despite the complexities of underwater adaptation, our method produces images at unparalleled speeds with superior details. Moreover, it reveals distant scene details with far greater clarity than other methods, dramatically improving reconstructed and rendered images. We demonstrate results on existing datasets and a new dataset we have collected. Additional visual results are available at: https://bgu-cs-vil.github.io/gaussiansplashingUW.github.io/ .
format Preprint
id arxiv_https___arxiv_org_abs_2411_19588
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Gaussian Splashing: Direct Volumetric Rendering Underwater
Mualem, Nir
Amoyal, Roy
Freifeld, Oren
Akkaynak, Derya
Computer Vision and Pattern Recognition
In underwater images, most useful features are occluded by water. The extent of the occlusion depends on imaging geometry and can vary even across a sequence of burst images. As a result, 3D reconstruction methods robust on in-air scenes, like Neural Radiance Field methods (NeRFs) or 3D Gaussian Splatting (3DGS), fail on underwater scenes. While a recent underwater adaptation of NeRFs achieved state-of-the-art results, it is impractically slow: reconstruction takes hours and its rendering rate, in frames per second (FPS), is less than 1. Here, we present a new method that takes only a few minutes for reconstruction and renders novel underwater scenes at 140 FPS. Named Gaussian Splashing, our method unifies the strengths and speed of 3DGS with an image formation model for capturing scattering, introducing innovations in the rendering and depth estimation procedures and in the 3DGS loss function. Despite the complexities of underwater adaptation, our method produces images at unparalleled speeds with superior details. Moreover, it reveals distant scene details with far greater clarity than other methods, dramatically improving reconstructed and rendered images. We demonstrate results on existing datasets and a new dataset we have collected. Additional visual results are available at: https://bgu-cs-vil.github.io/gaussiansplashingUW.github.io/ .
title Gaussian Splashing: Direct Volumetric Rendering Underwater
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2411.19588