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 experi-ments 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.
We first employ the pseudo-depth Gaussian complementation to enrich the primitives initialized by COLMAP. Then we utilize the plenoptic medium representation to estimate the medium parameter and render the underwater images. Our network is optimized with the loss function, including a new depth ranking regularized loss.
Below, you can choose different scenes for comparison. On the left, you can see the comparison between WaterSplatting and Plenodium in underwater scene reconstruction. On the right, you can see the comparison between WaterSplatting and Plenodium in underwater scene restoration.
Below, you can choose different degradation intensity for comparison. On the left, you can see the comparison between WaterSplatting and Plenodium in Fog scene restoration. On the right, you can see the comparison between WaterSplatting and Plenodium in Water scene restoration.