从复原到重建：重新思考水下场景的3D高斯泼溅
From Restoration to Reconstruction: Rethinking 3D Gaussian Splatting for Underwater Scenes
AI总结：
本文提出R-Splatting框架，将水下图像复原与3D高斯泼溅统一结合，通过多增强视图整合、光照生成器及不确定性感知不透明度优化，在Seathru-NeRF和BlueCoral3D数据集上同时提升了水下场景的渲染质量与几何精度。
摘要：
水下图像退化对3D重建构成重大挑战，简化的物理模型在复杂场景中往往失效。我们提出R-Splatting，一个统一框架，将水下图像复原（UIR）与3D高斯泼溅（3DGS）桥接起来，以同时提升渲染质量和几何保真度。我们的方法将多种UIR模型生成的多增强视图整合到单一重建流程中。在推理阶段，一个轻量级光照生成器采样潜码以支持多样且连贯的渲染，同时对比损失确保解耦且稳定的光照表示。此外，我们提出不确定性感知不透明度优化（UAOO），将不透明度建模为随机函数以正则化训练。这抑制了由光照变化触发的突变梯度响应，并缓解了对噪声或视角特定伪影的过拟合。在Seathru-NeRF和我们新的BlueCoral3D数据集上的实验表明，R-Splatting在渲染质量和几何精度上均优于强基线方法。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
