Ocean4D: Generative Underwater 4D Reconstruction via Medium-Aware Video Diffusion
This work addresses the challenging problem of 4D reconstruction in underwater environments for computer vision and robotics, where existing in-air methods fail due to absorption, scattering, and dynamic disturbances.
Ocean4D tackles underwater 4D reconstruction by proposing a generative framework with a 4D geometrically consistent conditioning and a medium-aware denoising block, achieving state-of-the-art performance on dynamic and static underwater benchmarks.
Underwater 4D reconstruction remains challenging due to the coupling between degraded light transport in participating media and dynamic water variations. Most existing Methods are developed under in-air assumptions and do not explicitly account for underwater absorption and backscatter. Additionally, near-static assumptions make these approaches sensitive to drifting particles and dynamic distractors , leading to unstable geometry and inconsistent cross-view results. To address these issues, we propose a generative framework for underwater 4D reconstruction, named Ocean4D, which is built on two complementary components. Specifically, 4D-GCC constructs 4D geometrically consistent conditioning with improved cross-frame coverage, while the Medium-Aware Block performs implicit medium-aware denoising in the latent diffusion process to stabilize underwater appearance under absorption and scattering. Given a monocular video and target cameras, our method generates videos along the target trajectories while preserving global structure and cross-view consistency. Extensive experiments on both dynamic and static underwater benchmarks demonstrate state-of-the-art performance on underwater reconstruction.