发表机构
University of Bristol; National University of Singapore; National Park Service’s Submerged Resources Center（布里斯托大学; 新加坡国立大学; 国家公园管理局水下资源中心）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
OceanXL提出分块划分与自适应剪枝的3DGS框架，实现大规模水下三维重建的高效训练与紧凑表示，在多个数据集上验证了其可扩展性和质量优势。
AI 中文摘要
水下三维重建对于海洋勘探、生态监测以及海底基础设施检查至关重要，然而由于光衰减、散射以及有限的采集覆盖范围，在大规模场景下仍面临挑战。尽管3D高斯泼溅（3DGS）能够实现高质量实时渲染，但其在大规模水下场景中的应用受到高内存消耗和广阔区域优化效率低下的制约。我们提出OceanXL，一种基于3DGS的快速且可扩展的大规模水下重建框架。OceanXL采用分而治之策略，将场景划分为空间连贯的块，以实现高效优化，同时保持全局几何一致性。我们进一步引入一种针对水下条件定制的自适应剪枝方案，该方案移除冗余基元，在不牺牲视觉保真度的前提下生成紧凑表示。这些组件共同提升了大规模场景的训练效率和渲染性能。我们还引入了一个覆盖多种海洋环境的大规模水下数据集。在五个大规模场景上的实验表明，相较于大规模场景基线，OceanXL在可扩展性、紧凑性以及效率-质量权衡方面表现出色。在小型SeaThru-NeRF数据集上的受控比较进一步显示，OceanXL在模型尺寸大幅小于水下专用方法的情况下，实现了具有竞争力的重建质量。
英文摘要
Underwater 3D reconstruction is critical for marine exploration, ecological monitoring, and subsea infrastructure inspection, yet remains challenging at large scale due to light attenuation, scattering, and limited capture coverage. While 3D Gaussian Splatting (3DGS) enables high-quality real-time rendering, its application to large underwater scenes is constrained by high memory consumption and inefficient optimization over extensive areas. We propose OceanXL, a fast and scalable 3DGS-based framework for large-scale underwater reconstruction. OceanXL adopts a divide-and-conquer strategy, partitioning scenes into spatially coherent blocks to enable efficient optimization while preserving global geometric consistency. We further introduce an adaptive pruning scheme tailored to underwater conditions that removes redundant primitives, producing compact representations without sacrificing visual fidelity. Together, these components improve training efficiency and rendering performance for large scenes. We also introduce a large-scale underwater dataset covering diverse marine environments. Experiments on five large-scale scenes demonstrate favorable scalability, compactness, and efficiency--quality trade-offs over large-scene baselines. Controlled comparisons on the small-scale SeaThru-NeRF dataset further show competitive reconstruction quality with substantially smaller model sizes than underwater-specific methods.
CommentsSIGGRAPH ASIA 2026
