用新表示法提升水下3D重建精度，兼顾物体与介质效果
Plenodium: UnderWater 3D Scene Reconstruction with Plenoptic Medium Representation
- 用球谐函数编码方向与位置信息，统一建模物体和水下介质
- 在真实数据集上重建误差降低23.6%，深度排序损失提升深度一致性
- 适合做水下三维重建、海洋探测或虚拟现实的科研人员使用
我们提出Plenodium（plenoptic medium），一种高效且有效的3D表示框架，能够联合建模物体和参与性介质。与仅依赖视角依赖建模的现有介质表示方法不同，我们的新型光锥介质表示通过球谐函数编码同时包含方向和位置信息，实现高精度的水下场景重建。为应对退化水下环境中的初始化难题，我们提出伪深度高斯补全方法，以鲁棒深度先验增强COLMAP生成的点云。此外，设计了深度排序正则化损失，优化场景几何并提升深度图的序数一致性。在真实水下数据集上的大量实验表明，该方法显著提升了3D重建效果。我们还构建了一个带真实标注和可控散射介质的模拟数据集，验证了方法在水下场景中的恢复能力。代码与数据集已公开于https://plenodium.github.io/。
原文摘要 · Abstract (English)
We present Plenodium (plenoptic medium), an effective and efficient 3D representation framework capable of jointly modeling both objects and participating media. In contrast to existing medium representations that rely solely on view-dependent modeling, our novel plenoptic medium representation incorporates both directional and positional information through spherical harmonics encoding, enabling highly accurate underwater scene reconstruction. To address the initialization challenge in degraded underwater environments, we propose the pseudo-depth Gaussian complementation to augment COLMAP-derived point clouds with robust depth priors. In addition, a depth ranking regularized loss is developed to optimize the geometry of the scene and improve the ordinal consistency of the depth maps. Extensive experiments on real-world underwater datasets demonstrate that our method achieves significant improvements in 3D reconstruction. Furthermore, we conduct a simulated dataset with ground truth and the controllable scattering medium to demonstrate the restoration capability of our method in underwater scenarios. Our code and dataset are available at https://plenodium.github.io/.
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。