Plenodium: UnderWater 3D Scene Reconstruction with Plenoptic Medium Representation
This addresses the problem of degraded underwater reconstruction for robotics or marine research, with incremental advances in representation and optimization.
The paper tackles underwater 3D scene reconstruction by proposing Plenodium, a representation that models objects and participating media using spherical harmonics encoding, achieving significant improvements in accuracy on real-world datasets.
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/.