用三视角一致性提升水下场景重建精度，减少散射干扰
OceanSplat: Object-aware Gaussian Splatting with Trinocular View Consistency for Underwater Scene Reconstruction
- 通过虚拟三视角增强视图一致性，约束3D高斯分布
- 利用虚拟视点生成深度先验，弥补水下几何信息不足
- 深度感知透明度调整，抑制介质伪影，适合水下视觉任务
我们提出OceanSplat，一种基于3D高斯点阵的水下场景高保真重建方法。为克服散射介质导致的多视角不一致问题，我们在每个相机位姿下通过水平与垂直平移生成虚拟视点，构建三视角结构，强制视图一致性以优化3D高斯的空间分布。同时，从虚拟视点推导出合成对极深度先验，作为自监督深度正则项，补偿退化水下场景中的几何线索缺失。此外，提出深度感知的alpha调节机制，在早期训练中根据3D高斯沿视线方向的深度动态调整其透明度，防止介质诱导的伪结构形成。该方法通过有效几何约束实现3D高斯与散射介质的解耦，准确还原场景结构，显著减少悬浮伪影。在真实水下及模拟场景上的实验表明，OceanSplat在散射介质中的场景重建与恢复效果显著优于现有方法。
原文摘要 · Abstract (English)
We introduce OceanSplat, a novel 3D Gaussian Splatting-based approach for high-fidelity underwater scene reconstruction. To overcome multi-view inconsistencies caused by scattering media, we design a trinocular setup for each camera pose by rendering from horizontally and vertically translated virtual viewpoints, enforcing view consistency to facilitate spatial optimization of 3D Gaussians. Furthermore, we derive synthetic epipolar depth priors from the virtual viewpoints, which serve as self-supervised depth regularizers to compensate for the limited geometric cues in degraded underwater scenes. We also propose a depth-aware alpha adjustment that modulates the opacity of 3D Gaussians during early training based on their depth along the viewing direction, deterring the formation of medium-induced primitives. Our approach promotes the disentanglement of 3D Gaussians from the scattering medium through effective geometric constraints, enabling accurate representation of scene structure and significantly reducing floating artifacts. Experiments on real-world underwater and simulated scenes demonstrate that OceanSplat substantially outperforms existing methods for both scene reconstruction and restoration in scattering media.
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。