WaterSplatting：使用高斯泼溅的快速水下3D场景重建
WaterSplatting: Fast Underwater 3D Scene Reconstruction Using Gaussian Splatting
AI总结：
提出融合体积渲染与3DGS的水下场景重建方法，利用3DGS表示几何并用体积场捕捉水介质，在SeaThru-NeRF数据集上实现优于NeRF的渲染质量与实时性能。
摘要：
水下3D场景重建是一个极具挑战性且有趣的问题，其应用范围涵盖从海军机器人到VR体验。基于完全体积的NeRF方法成功解决了该问题，这些方法能够同时对几何形状和介质（水）进行建模。然而，这些方法训练速度慢，且无法提供实时渲染。最近，3D Gaussian Splatting (3DGS) 方法为 NeRFs 提供了一种快速的替代方案。但是，由于它是一种仅渲染几何形状的显式方法，它无法渲染介质，因此不适用于水下重建。为此，我们提出了一种将体积渲染与 3DGS 相融合的新方法，以有效处理水下数据。我们的方法采用 3DGS 进行显式几何表示，并使用一个单独的体积场（每个像素查询一次）来捕捉散射介质。这种双重表示进一步允许通过移除散射介质来恢复场景。在 underwater SeaThru-NeRF 数据集上，我们的方法在渲染质量上优于基于 NeRF 的最先进方法。此外，它在提供实时渲染性能的同时做到了这一点，从而解决了现有方法的效率限制。
英文摘要：
The underwater 3D scene reconstruction is a challenging, yet interesting problem with applications ranging from naval robots to VR experiences. The problem was successfully tackled by fully volumetric NeRF-based methods which can model both the geometry and the medium (water). Unfortunately, these methods are slow to train and do not offer real-time rendering. More recently, 3D Gaussian Splatting (3DGS) method offered a fast alternative to NeRFs. However, because it is an explicit method that renders only the geometry, it cannot render the medium and is therefore unsuited for underwater reconstruction. Therefore, we propose a novel approach that fuses volumetric rendering with 3DGS to handle underwater data effectively. Our method employs 3DGS for explicit geometry representation and a separate volumetric field (queried once per pixel) for capturing the scattering medium. This dual representation further allows the restoration of the scenes by removing the scattering medium. Our method outperforms state-of-the-art NeRF-based methods in rendering quality on the underwater SeaThru-NeRF dataset. Furthermore, it does so while offering real-time rendering performance, addressing the efficiency limitations of existing methods. Web: https://water-splatting.github.io
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。
