From Restoration to Reconstruction: Rethinking 3D Gaussian Splatting for Underwater Scenes

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Huang, Guoxi, Wang, Haoran, Qi, Zipeng, Lu, Wenjun, Bull, David, Anantrasirichai, Nantheera
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909799631814656
author Huang, Guoxi
Wang, Haoran
Qi, Zipeng
Lu, Wenjun
Bull, David
Anantrasirichai, Nantheera
author_facet Huang, Guoxi
Wang, Haoran
Qi, Zipeng
Lu, Wenjun
Bull, David
Anantrasirichai, Nantheera
contents Underwater image degradation poses significant challenges for 3D reconstruction, where simplified physical models often fail in complex scenes. We propose \textbf{R-Splatting}, a unified framework that bridges underwater image restoration (UIR) with 3D Gaussian Splatting (3DGS) to improve both rendering quality and geometric fidelity. Our method integrates multiple enhanced views produced by diverse UIR models into a single reconstruction pipeline. During inference, a lightweight illumination generator samples latent codes to support diverse yet coherent renderings, while a contrastive loss ensures disentangled and stable illumination representations. Furthermore, we propose \textit{Uncertainty-Aware Opacity Optimization (UAOO)}, which models opacity as a stochastic function to regularize training. This suppresses abrupt gradient responses triggered by illumination variation and mitigates overfitting to noisy or view-specific artifacts. Experiments on Seathru-NeRF and our new BlueCoral3D dataset demonstrate that R-Splatting outperforms strong baselines in both rendering quality and geometric accuracy.
format Preprint
id arxiv_https___arxiv_org_abs_2509_17789
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle From Restoration to Reconstruction: Rethinking 3D Gaussian Splatting for Underwater Scenes
Huang, Guoxi
Wang, Haoran
Qi, Zipeng
Lu, Wenjun
Bull, David
Anantrasirichai, Nantheera
Computer Vision and Pattern Recognition
Underwater image degradation poses significant challenges for 3D reconstruction, where simplified physical models often fail in complex scenes. We propose \textbf{R-Splatting}, a unified framework that bridges underwater image restoration (UIR) with 3D Gaussian Splatting (3DGS) to improve both rendering quality and geometric fidelity. Our method integrates multiple enhanced views produced by diverse UIR models into a single reconstruction pipeline. During inference, a lightweight illumination generator samples latent codes to support diverse yet coherent renderings, while a contrastive loss ensures disentangled and stable illumination representations. Furthermore, we propose \textit{Uncertainty-Aware Opacity Optimization (UAOO)}, which models opacity as a stochastic function to regularize training. This suppresses abrupt gradient responses triggered by illumination variation and mitigates overfitting to noisy or view-specific artifacts. Experiments on Seathru-NeRF and our new BlueCoral3D dataset demonstrate that R-Splatting outperforms strong baselines in both rendering quality and geometric accuracy.
title From Restoration to Reconstruction: Rethinking 3D Gaussian Splatting for Underwater Scenes
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2509.17789