Benchmarking Neural Rendering Approaches for 3D Reconstruction of Underwater Environments

Salvatore Mario Carota, Alessandro Privitera, Daniele Di Mauro, Antonino Furnari, Antonino Furnari, Giovanni Farinella, Giovanni Farinella, Francesco Ragusa, Francesco Ragusa

2025

Abstract

We tackle the problem of 3D reconstruction of underwater scenarios using neural rendering techniques. We propose a benchmark adopting the SeaThru-NeRF dataset, performing a systematic analysis by comparing several established methods based on NERF and 3D Gaussian Splatting through a series of experiments. The results were evaluated both quantitatively, using various 2D and 3D metrics, and qualitatively, through a user survey assessing the fidelity of the reconstructed images. This serves to provide critical insight into how to select the optimal techniques for 3D reconstruction of underwater scenarios. The results indicate that, in the context of this application, among the algorithms tested, NeRF-based methods performed better in both mesh generation and novel view synthesis than the 3D Gaussian Splatting based methods.

Paper Citation

in Harvard Style

Carota S., Privitera A., Di Mauro D., Furnari A., Farinella G. and Ragusa F. (2025). Benchmarking Neural Rendering Approaches for 3D Reconstruction of Underwater Environments. In Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP; ISBN 978-989-758-728-3, SciTePress, pages 766-773. DOI: 10.5220/0013381200003912

in Bibtex Style

@conference{visapp25,
author={Salvatore Carota and Alessandro Privitera and Daniele Di Mauro and Antonino Furnari and Giovanni Farinella and Francesco Ragusa},
title={Benchmarking Neural Rendering Approaches for 3D Reconstruction of Underwater Environments},
booktitle={Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP},
year={2025},
pages={766-773},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013381200003912},
isbn={978-989-758-728-3},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP
TI - Benchmarking Neural Rendering Approaches for 3D Reconstruction of Underwater Environments
SN - 978-989-758-728-3
AU - Carota S.
AU - Privitera A.
AU - Di Mauro D.
AU - Furnari A.
AU - Farinella G.
AU - Ragusa F.
PY - 2025
SP - 766
EP - 773
DO - 10.5220/0013381200003912
PB - SciTePress