发表机构
Zhejiang University; Shanghai AI Laboratory; Shanghai Jiao Tong University; Tsinghua University; The University of Hong Kong; The Chinese University of Hong Kong（浙江大学; 上海人工智能实验室; 上海交通大学; 清华大学; 香港大学; 香港中文大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对水下场景视觉退化导致的SLAM难题，提出AquaFlow框架，通过微调3D视觉基础模型等技术实现更优的水下重建，在62条水下轨迹数据集上相较WaterSplat-SLAM性能显著提升。
AI 中文摘要
近期的单目三维高斯溅射（3DGS）流式重建方法通过平衡重建质量与效率取得了出色性能，但将这些框架扩展至水下场景仍面临挑战，因为水下存在严重的视觉退化问题，如光衰减和散射，这会降低相机位姿跟踪精度并扭曲场景几何结构。为应对这些挑战，我们提出AquaFlow——一种用于高效高保真水下重建的单目高斯溅射流式重建框架。具体而言，AquaFlow在大规模水下数据上微调三维视觉基础模型，以实现鲁棒的位姿与点云图估计；同时引入一种介质引导的增量高斯初始化策略用于流式建图；此外，我们开发了一种兼容流式的混合场景表示，将结构化的、距离条件化的神经高斯与受物理启发的光学模型相结合，以补偿水下成像效应，实现精准的场景重建。我们在包含62条不同水下轨迹的综合数据集上评估AquaFlow，该数据集来自公开基准及不同规模的野外网络视频。大量实验表明，AquaFlow达到了领先的跟踪与渲染性能，与WaterSplat-SLAM相比，平均定位误差降低13.2%，峰值信噪比（PSNR）提升4.74 dB。
英文摘要
Recent monocular 3D Gaussian Splatting (3DGS) streaming reconstruction methods have achieved impressive performance by balancing reconstruction quality and efficiency. However, extending these frameworks to underwater scenes remains challenging due to severe visual degradation, such as light attenuation and scattering, which degrades camera pose tracking and distorts scene geometry. To address these challenges, we propose AquaFlow, a monocular Gaussian Splatting streaming reconstruction framework for efficient and high-fidelity underwater reconstruction. Specifically, AquaFlow fine-tunes a 3D vision foundation model on large-scale underwater data for robust pose and pointmap estimation, and introduces a medium-guided incremental Gaussian initialization strategy for streaming mapping. Furthermore, we develop a streaming-compatible hybrid scene representation that integrates structured, distance-conditioned neural Gaussians with a physics-inspired optical model to compensate for underwater image formation effects, enabling accurate scene reconstruction. We evaluate AquaFlow on a comprehensive dataset of 62 diverse underwater trajectories, collected from both public benchmarks and in-the-wild web videos across various scales. Extensive experiments demonstrate that AquaFlow achieves state-of-the-art tracking and rendering performance, reducing average localization error by 13.2% and improving PSNR by 4.74 dB compared to WaterSplat-SLAM.
CommentsPreprint
