针对水下场景优化的3D高斯点云重建方法，提升远距离清晰度与动态物体处理能力。
UW-GS: Distractor-Aware 3D Gaussian Splatting for Enhanced Underwater Scene Reconstruction
- 引入距离相关颜色模型和物理密度控制，改善水下光照效果
- 使用二值运动掩码处理动态物体，结合伪深度图提升重建质量
- 在新数据集S-UW上实现最高1.26dB的PSNR提升，适合水下三维重建应用
3D高斯点云渲染（3DGS）可实现实时高质量三维场景重建，但其假设场景处于透明介质中，在存在光吸收与散射、且含移动物体的水下环境中表现不佳。为此，本文提出专为水下场景设计的UW-GS方法：引入距离相关的颜色变化模型，采用基于物理的密度控制策略增强远距离物体清晰度，并利用二值运动掩码处理动态内容。通过设计支持散射介质的损失函数并结合伪深度图进行优化，UW-GS在定量指标上优于现有方法，最高实现1.26dB的PSNR提升。为全面验证模型有效性，本文还构建了包含动态物体掩码的新水下数据集S-UW。
原文摘要 · Abstract (English)
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.
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。