Gaussian Splashing：水下直接体渲染
Gaussian Splashing: Direct Volumetric Rendering Underwater
AI总结：
提出Gaussian Splashing方法，结合3DGS与水下散射成像模型，实现快速高质量的水下3D重建与渲染，速度达140 FPS，显著提升细节清晰度。
摘要：
在水下图像中，大多数有用的特征被水遮挡。遮挡的程度取决于成像几何，甚至在连续拍摄的图像序列中也会有所变化。因此，在空气中场景表现稳健的3D重建方法，如Neural Radiance Field方法（NeRFs）或3D Gaussian Splatting（3DGS），在水下场景中会失败。虽然最近针对NeRFs的水下适配取得了state-of-the-art的结果，但它的速度慢得不切实际：重建需要数小时，且其渲染速率（以每秒帧数FPS计）低于1。在此，我们提出了一种新方法，仅需几分钟即可完成重建，并能以140 FPS渲染新颖的水下场景。该方法名为Gaussian Splashing，将3DGS的优势与速度与用于捕捉散射的图像形成模型相统一，在渲染和深度估计流程以及3DGS损失函数中引入了创新。尽管水下适配具有复杂性，我们的方法以无与伦比的速度生成了具有卓越细节的图像。此外，它比其他方法更清晰地揭示了远处场景细节，显著改善了重建和渲染的图像。我们在现有数据集和我们收集的新数据集上展示了结果。
英文摘要：
In underwater images, most useful features are occluded by water. The extent of the occlusion depends on imaging geometry and can vary even across a sequence of burst images. As a result, 3D reconstruction methods robust on in-air scenes, like Neural Radiance Field methods (NeRFs) or 3D Gaussian Splatting (3DGS), fail on underwater scenes. While a recent underwater adaptation of NeRFs achieved state-of-the-art results, it is impractically slow: reconstruction takes hours and its rendering rate, in frames per second (FPS), is less than 1. Here, we present a new method that takes only a few minutes for reconstruction and renders novel underwater scenes at 140 FPS. Named Gaussian Splashing, our method unifies the strengths and speed of 3DGS with an image formation model for capturing scattering, introducing innovations in the rendering and depth estimation procedures and in the 3DGS loss function. Despite the complexities of underwater adaptation, our method produces images at unparalleled speeds with superior details. Moreover, it reveals distant scene details with far greater clarity than other methods, dramatically improving reconstructed and rendered images. We demonstrate results on existing datasets and a new dataset we have collected. Additional visual results are available at: https://bgu-cs-vil.github.io/gaussiansplashingUW.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。
