WAT3R: Feedforward Underwater 3D Reconstruction

Jiayi Xu1, Jiahao Lu1, Ziqiang Zheng1, Yihao Tan2, Yaolong Zhu3, Yuan Liu1, Sai-Kit Yeung1
1The Hong Kong University of Science and Technology, 2The Chinese University of Hong Kong, 3Peking University
Overview.

WAT3R is a feed-forward framework for reconstructing 3D scenes directly from underwater images, integrating a lightweight neural adaptation module to account for underwater degradation effects and outputting pixel-aligned 3D point maps and camera poses in a single forward pass.

Abstract

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.

Methodology

Method overview.

Overview of the WAT3R framework. Our method integrates a degradation adaptation module with a 3D reconstruction pipeline. By incorporating an underwater image formation model, WAT3R utilizes degradation-aware adaptation to implicitly refine depth estimation and 3D point cloud estimation from original images.

3D Reconstruction

We show the 3D reconstruction results of WAT3R on underwater video sequences, outputting pixel-aligned 3D point maps and camera poses in a single forward pass.

Color Restoration

Here we show the underwater image restoration results of WAT3R. Drag the slider to compare the original underwater frame (left) with the restored output (right).

BibTeX

@misc{xu2026wat3rfeedforwardunderwater3d,
      title={WAT3R: Feedforward Underwater 3D Reconstruction}, 
      author={Jiayi Xu and Jiahao Lu and Ziqiang Zheng and Yihao Tan and Yaolong Zhu and Yuan Liu and Sai-Kit Yeung},
      year={2026},
      eprint={2607.21023},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2607.21023}}