快速高质还原水下3D场景，实时渲染达140帧。
Gaussian Splashing: Direct Volumetric Rendering Underwater
- 结合3DGS与散射成像模型，优化渲染与深度估计。
- 重建仅需几分钟，渲染速度达140 FPS，远超现有方法。
- 适合水下三维重建、实时可视化应用，效果显著提升。
水下图像中，多数有用特征被水体遮挡，遮挡程度受成像几何影响，甚至在连续快照序列中也存在差异。因此，适用于空气场景的3D重建方法（如NeRF或3DGS）在水下失效。尽管近期有水下NeRF改进方案达到顶尖性能，但其重建耗时数小时，渲染速率低于1帧/秒，不具实用性。本文提出新方法Gaussian Splashing，仅需几分钟完成重建，实现140帧/秒的实时渲染。该方法融合3DGS的速度优势与水下散射成像模型，在渲染、深度估计及损失函数上引入创新。即使面对复杂的水下环境，仍能以极快速度生成细节丰富的图像，并显著揭示远距离场景细节，大幅优于现有方法。我们在现有数据集及自建新数据集上验证了效果，更多视觉结果见：https://bgu-cs-vil.github.io/gaussiansplashingUW.github.io/
原文摘要 · Abstract (English)
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/ .
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。