WAT3R: Feedforward Underwater 3D Reconstruction
This work addresses the challenging problem of underwater 3D reconstruction for autonomous systems and marine research, offering a practical feedforward solution.
WAT3R introduces a feedforward framework for underwater 3D reconstruction that handles light attenuation and backscattering via a lightweight neural adaptation module, achieving state-of-the-art results on FLSea, SQUID, and USOD10K datasets for depth and pose estimation.
Reliable feedforward underwater 3D reconstruction remains challenging due to severe light attenuation and backscattering, which degrade visual quality and disrupt feature consistency across views, leading to inaccurate multi-view geometry. To address this issue, we propose WAT3R, a feed-forward framework for reconstructing 3D scenes directly from underwater images. By leveraging degradation adaptation as a geometry-constrained process, WAT3R integrates a lightweight neural adaptation module to flexibly account for these underwater imaging effects, thereby improving multi-view reconstruction quality. Implemented in a single forward pass, WAT3R directly and efficiently outputs pixel-aligned 3D point maps and camera poses from underwater videos, allowing a high-quality underwater 3D reconstruction. Experiments conducted on the FLSea, SQUID, and USOD10K datasets show that our method consistently outperforms state-of-the-art approaches on 3D reconstruction tasks, including multi-view/monocular depth estimation and camera pose estimation.