3D-UIR: 基于物理的3D场景重建中的3D高斯方法用于水下3D场景重建
3D-UIR: 3D Gaussian for Underwater 3D Scene Reconstruction via Physics Based Appearance-Medium Decoupling
AI总结：
本文提出一种基于物理的框架，通过定制的高斯建模分离物体外观与水介质影响，提升水下场景重建的几何一致性和渲染质量。
摘要：
水下场景重建的新型视图合成面临独特挑战，由于复杂的光-介质相互作用。水体中的散射和吸收导致不均匀的介质衰减干扰，破坏了传统体积渲染对均匀传播介质的假设。尽管3D高斯点云（3DGS）提供了实时渲染能力，但在水下不均匀环境中，散射介质会引入伪影和不一致的外观。在本研究中，我们提出了一种基于物理的框架，通过定制的高斯建模分离物体外观与水介质影响。我们的方法引入了外观嵌入，这些是显式的介质表示，用于后向散射和衰减，增强场景一致性。此外，我们提出了一种基于深度的优化策略，利用伪深度图作为监督，并通过深度正则化和尺度惩罚项来提高几何保真度。通过整合所提出的外观和介质建模组件，通过水下成像模型，我们的方法实现了高质量的新型视图合成和物理准确的场景恢复。实验表明，我们的方法在渲染质量和恢复准确性方面显著优于现有方法。项目页面可在https://bilityniu.github.io/3D-UIR上找到。
英文摘要：
Novel view synthesis for underwater scene reconstruction presents unique challenges due to complex light-media interactions. Optical scattering and absorption in water body bring inhomogeneous medium attenuation interference that disrupts conventional volume rendering assumptions of uniform propagation medium. While 3D Gaussian Splatting (3DGS) offers real-time rendering capabilities, it struggles with underwater inhomogeneous environments where scattering media introduces artifacts and inconsistent appearance. In this study, we propose a physics-based framework that disentangles object appearance from water medium effects through tailored Gaussian modeling. Our approach introduces appearance embeddings, which are explicit medium representations for backscatter and attenuation, enhancing scene consistency. In addition, we propose a depth-guided optimization strategy that leverages pseudo-depth maps as supervision with depth regularization and scale penalty terms to improve geometric fidelity. By integrating the proposed appearance and medium modeling components via an underwater imaging model, our approach achieves both high-quality novel view synthesis and physically accurate scene restoration. Experiments demonstrate our significant improvements in rendering quality and restoration accuracy over existing methods. The project page is available at https://bilityniu.github.io/3D-UIR.
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。
