UW-GS：用于增强水下场景重建的干扰物感知3D高斯泼溅
UW-GS: Distractor-Aware 3D Gaussian Splatting for Enhanced Underwater Scene Reconstruction
AI总结：
针对3DGS在水下场景因光吸收、散射和动态物体导致渲染效果差的问题，提出UW-GS方法，通过距离相关颜色外观、物理密度控制和运动掩码优化表示，PSNR增益达1.26dB，并构建了新数据集S-UW。
摘要：
3D高斯泼溅（3DGS）具备实现实时高质量3D场景渲染的能力。然而，3DGS假设场景处于清澈介质环境中，在水下场景中难以生成令人满意的表示，因为这些场景普遍存在光吸收和散射，且涉及运动物体。为克服这些问题，我们引入了一种新颖的基于高斯泼溅的方法UW-GS，专为水下应用设计。它引入了一种建模距离相关颜色变化的颜色外观，采用新的基于物理的密度控制策略以增强远处物体的清晰度，并使用二值运动掩码来处理动态内容。通过精心设计的支持散射介质的损失函数进行优化，并由伪深度图增强，UW-GS优于现有方法，PSNR增益最高达1.26dB。为充分验证模型有效性，我们还开发了带有动态物体掩码的新水下数据集S-UW。
英文摘要：
3D Gaussian splatting (3DGS) offers the capability to achieve real-time high quality 3D scene rendering. However, 3DGS assumes that the scene is in a clear medium environment and struggles to generate satisfactory representations in underwater scenes, where light absorption and scattering are prevalent and moving objects are involved. To overcome these, we introduce a novel Gaussian Splatting-based method, UW-GS, designed specifically for underwater applications. It introduces a color appearance that models distance-dependent color variation, employs a new physics-based density control strategy to enhance clarity for distant objects, and uses a binary motion mask to handle dynamic content. Optimized with a well-designed loss function supporting for scattering media and strengthened by pseudo-depth maps, UW-GS outperforms existing methods with PSNR gains up to 1.26dB. To fully verify the effectiveness of the model, we also developed a new underwater dataset, S-UW, with dynamic object masks.
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。
