# WAT3R: Feedforward Underwater 3D Reconstruction

arXiv: https://arxiv.org/abs/2607.21023 · HTML: https://mlsanity.com/paper/2607.21023/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 46 references that are in the map.
- First posted on arXiv 23 Jul 2026.

## Builds on (most cited first, 26 of 26)

- [Vision Transformers for Dense Prediction](https://mlsanity.com/paper/2103.13413/) (2021)
- [DUSt3R: Geometric 3D Vision Made Easy](https://mlsanity.com/paper/2312.14132/) (2023)
- [VGGT: Visual Geometry Grounded Transformer](https://mlsanity.com/paper/2503.11651/) (2025)
- [MUSIQ: Multi-scale Image Quality Transformer](https://mlsanity.com/paper/2108.05997/) (2021)
- [ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual-Inertial and Multi-Map SLAM](https://mlsanity.com/paper/2007.11898/) (2020)
- [TartanAir: A Dataset to Push the Limits of Visual SLAM](https://mlsanity.com/paper/2003.14338/) (2020)
- [MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion](https://mlsanity.com/paper/2410.03825/) (2024)
- [Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Pass](https://mlsanity.com/paper/2501.13928/) (2025)
- [π3: Permutation-Equivariant Visual Geometry Learning](https://mlsanity.com/paper/2507.13347/) (2025)
- [DeepMVS: Learning Multi-view Stereopsis](https://mlsanity.com/paper/1804.00650/) (2018)
- [An Underwater Image Enhancement Benchmark Dataset and Beyond](https://mlsanity.com/paper/1901.05495/) (2019)
- [FLARE: Feed-forward Geometry, Appearance and Camera Estimation from Uncalibrated Sparse Views](https://mlsanity.com/paper/2502.12138/) (2025)
- [U-shape Transformer for Underwater Image Enhancement](https://mlsanity.com/paper/2111.11843/) (2021)
- [Underwater Single Image Color Restoration Using Haze-Lines and a New Quantitative Dataset](https://mlsanity.com/paper/1811.01343/) (2018)
- [Align3R: Aligned Monocular Depth Estimation for Dynamic Videos](https://mlsanity.com/paper/2412.03079/) (2024)
- [SeaThru-NeRF: Neural Radiance Fields in Scattering Media](https://mlsanity.com/paper/2304.07743/) (2023)
- [WaterSplatting: Fast Underwater 3D Scene Reconstruction Using Gaussian Splatting](https://mlsanity.com/paper/2408.08206/) (2024)
- [SeaSplat: Representing Underwater Scenes with 3D Gaussian Splatting and a Physically Grounded Image Formation Model](https://mlsanity.com/paper/2409.17345/) (2024)
- [WaterNeRF: Neural Radiance Fields for Underwater Scenes](https://mlsanity.com/paper/2209.13091/) (2022)
- [UDepth: Fast Monocular Depth Estimation for Visually-guided Underwater Robots](https://mlsanity.com/paper/2209.12358/) (2022)
- [FLSea: Underwater Visual-Inertial and Stereo-Vision Forward-Looking Datasets](https://mlsanity.com/paper/2302.12772/) (2023)
- [UVEB: A Large-scale Benchmark and Baseline Towards Real-World Underwater Video Enhancement](https://mlsanity.com/paper/2404.14542/) (2024)
- [Osmosis: RGBD Diffusion Prior for Underwater Image Restoration](https://mlsanity.com/paper/2403.14837/) (2024)
- [Metrically Scaled Monocular Depth Estimation through Sparse Priors for Underwater Robots](https://mlsanity.com/paper/2310.16750/) (2023)
- [WaterHE-NeRF: Water-ray Tracing Neural Radiance Fields for Underwater Scene Reconstruction](https://mlsanity.com/paper/2312.06946/) (2023)
- [PierGuard: A Planning Framework for Underwater Robotic Inspection of Coastal Piers](https://mlsanity.com/paper/2505.07845/) (2025)

## Built on by (most cited first, 1 of 1)

- [FujinSplat: Seeing Through Smoke with RAW-Domain Gaussian Splatting](https://mlsanity.com/paper/2609.06017/) (2026)

## Abstract (arXiv)

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.