From Restoration to Reconstruction: Rethinking 3D Gaussian Splatting for Underwater Scenes
This addresses challenges in underwater 3D reconstruction for applications like marine exploration, but it is incremental as it builds on existing 3DGS and UIR methods.
The paper tackles the problem of 3D reconstruction in underwater scenes, where image degradation hinders quality, by proposing R-Splatting, which integrates underwater image restoration with 3D Gaussian Splatting to improve rendering and geometry, achieving superior results on datasets like Seathru-NeRF and BlueCoral3D.
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.