WAT3R: Feedforward Underwater 3D Reconstruction

• URL: http://arxiv.org/abs/2607.21023v1
• Date: Thu, 23 Jul 2026 08:07:43 GMT
• Title: WAT3R: Feedforward Underwater 3D Reconstruction
• Abstract summary: WAT3R is a feed-forward framework for reconstructing 3D scenes directly from underwater images.<n>By leveraging adaptation as a geometry-constrained process, WAT3R integrates a lightweight neural adaptation module.<n>We show that WAT3R consistently outperforms state-of-the-art approaches on 3D reconstruction tasks.
• Score: 33.441820956688396
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• 3D-USE: From Image-Level to Scene-Level Underwater Enhancement [54.11922584483346]
  Underwater Scene-level Enhancement (USE)<n>Uses a reliable scene representation for enhancement and a consistent enhancement target without paired enhanced 3D data.<n> Experiments on real underwater scenes show improved visibility and cross-view consistency while preserving reconstruction quality.
  arXiv  Detail & Related papers  (2026-08-28T07:34:13Z)
• AquaFlow: A Monocular Gaussian Splatting SLAM for Underwater Streaming Reconstruction [14.336895166294623]
  We propose AquaFlow, a streaming reconstruction framework for efficient and high-fidelity underwater reconstruction.<n>We fine-tunes a 3D vision foundation model on large-scale underwater data for robust pose and pointmap estimation.<n>We develop a streaming-compatible hybrid scene representation that integrates structured, distance-conditioned neural Gaussians with a physics-inspired optical model.
  arXiv  Detail & Related papers  (2026-08-24T07:39:07Z)
• Wat3R: Underwater 3D Geometry Learning without Annotations [58.91163632674025]
  Estimating 3D geometry in underwater environments presents unique challenges due to light attenuation, scattering, and the absence of large-scale, high-quality 3D annotations.<n>We propose Wat3R, a cross-domain semi-supervised learning framework designed to adapt feed-forward 3D reconstruction models from air to underwater scenes.
  arXiv  Detail & Related papers  (2026-07-09T17:59:58Z)
• Geometry-Aware Representation Denoising for Robust Multi-view 3D Reconstruction [36.377286063905395]
  We present Geometry-Aware Representation Denoising (GARD), a novel framework that performs diffusion-based multi-view restoration directly in the feature space of a feed-forward 3D reconstruction model.<n>This design exploits the geometry-aware feature representations of the 3D reconstructor to effectively recover accurate scene geometry.<n>By employing an additional RGB image decoder, the refined representations can also be used to restore high-quality RGB images.
  arXiv  Detail & Related papers  (2026-05-25T18:01:05Z)
• VISO: Robust Underwater Visual-Inertial-Sonar SLAM with Photometric Rendering for Dense 3D Reconstruction [2.095709224275874]
  VISO is a robust underwater SLAM system that fuses a stereo camera, an inertial measurement unit (IMU) and a 3D sonar.<n>We show that VISO surpasses current state-of-the-art underwater and visual-based SLAM algorithms in terms of localisation robustness and accuracy.
  arXiv  Detail & Related papers  (2026-01-03T10:18:09Z)
• From Restoration to Reconstruction: Rethinking 3D Gaussian Splatting for Underwater Scenes [13.730810237133822]
  We propose textbfR-Splatting, a unified framework that bridges underwater image restoration (UIR) with 3D Gaussian Splatting (3DGS)<n>Our method integrates multiple enhanced views produced by diverse UIR models into a single reconstruction pipeline.<n>Experiments on Seathru-NeRF and our new BlueCoral3D dataset demonstrate that R-Splatting outperforms strong baselines in both rendering quality and geometric accuracy.
  arXiv  Detail & Related papers  (2025-09-22T13:50:20Z)
• UW-SDF: Exploiting Hybrid Geometric Priors for Neural SDF Reconstruction from Underwater Multi-view Monocular Images [63.32490897641344]
  We propose a framework for reconstructing target objects from multi-view underwater images based on neural SDF. We introduce hybrid geometric priors to optimize the reconstruction process, markedly enhancing the quality and efficiency of neural SDF reconstruction.
  arXiv  Detail & Related papers  (2024-10-10T16:33:56Z)
• GEOcc: Geometrically Enhanced 3D Occupancy Network with Implicit-Explicit Depth Fusion and Contextual Self-Supervision [49.839374549646884]
  This paper presents GEOcc, a Geometric-Enhanced Occupancy network tailored for vision-only surround-view perception.<n>Our approach achieves State-Of-The-Art performance on the Occ3D-nuScenes dataset with the least image resolution needed and the most weightless image backbone.
  arXiv  Detail & Related papers  (2024-05-17T07:31:20Z)
• Scene 3-D Reconstruction System in Scattering Medium [9.044356059297595]
  Existing underwater 3D reconstruction systems still face challenges such as extensive training time and low efficiency. This paper proposes an improved underwater 3D reconstruction system to address these issues and achieve rapid, high-quality 3D reconstruction.
  arXiv  Detail & Related papers  (2023-12-14T14:55:16Z)
• R3D3: Dense 3D Reconstruction of Dynamic Scenes from Multiple Cameras [106.52409577316389]
  R3D3 is a multi-camera system for dense 3D reconstruction and ego-motion estimation. Our approach exploits spatial-temporal information from multiple cameras, and monocular depth refinement. We show that this design enables a dense, consistent 3D reconstruction of challenging, dynamic outdoor environments.
  arXiv  Detail & Related papers  (2023-08-28T17:13:49Z)
• Towards Non-Line-of-Sight Photography [48.491977359971855]
  Non-line-of-sight (NLOS) imaging is based on capturing the multi-bounce indirect reflections from the hidden objects. Active NLOS imaging systems rely on the capture of the time of flight of light through the scene. We propose a new problem formulation, called NLOS photography, to specifically address this deficiency.
  arXiv  Detail & Related papers  (2021-09-16T08:07:13Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.