From Restoration to Reconstruction: Rethinking 3D Gaussian Splatting for Underwater Scenes
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| 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 |