Wat3R: Underwater 3D Geometry Learning without Annotations

• URL: http://arxiv.org/abs/2607.08772v1
• Date: Thu, 09 Jul 2026 17:59:58 GMT
• Title: Wat3R: Underwater 3D Geometry Learning without Annotations
• Abstract summary: 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.
• Score: 58.91163632674025
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Estimating 3D geometry in underwater environments presents unique challenges due to light attenuation, scattering, and the absence of large-scale, high-quality 3D annotations. Pioneering methods rely on massive dense annotations that are impractical in underwater settings. In this paper, we propose Wat3R, a cross-domain semi-supervised learning framework designed to adapt feed-forward 3D reconstruction models from air to underwater scenes. Uniquely, our method eliminates the need for any annotated underwater data following a teacher-student architecture, that learns robust geometry representations merely on abundant unlabeled real underwater video footage. We also design a cross-view consistency loss that leverages geometric cues from other views to compensate for the information degradation in the current view caused by water attenuation and scattering. Furthermore, considering the lack of comprehensive evaluation benchmarks, we construct Water3D, a diverse dataset covering various water bodies and underwater scenarios, designed for geometric task evaluation. Experimental results demonstrate that Wat3R outperforms current state-of-the-art methods in underwater multi-view depth estimation and point cloud reconstruction. The dataset and code are available at https://github.com/LSXI7/Wat3R .

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)
• WAT3R: Feedforward Underwater 3D Reconstruction [33.441820956688396]
  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.
  arXiv  Detail & Related papers  (2026-07-23T08:07:43Z)
• Towards 3D karst underwater scene reconstruction from rotating sonar data [4.98552535993062]
  We present a pipeline for reconstructing underwater karst conduits from a sonar profiler.<n>We combine a continuous-time SLAM approach to correct trajectory drift with a novel two-stage deep learning method for surface reconstruction.
  arXiv  Detail & Related papers  (2026-06-18T15:02:00Z)
• Plenodium: UnderWater 3D Scene Reconstruction with Plenoptic Medium Representation [31.47797579690604]
  We present Plenodium, a 3D representation framework capable of jointly modeling both objects and participating media.<n>In contrast to existing medium representations that rely solely on view-dependent modeling, our novel plenoptic medium representation incorporates both directional and positional information.<n>Experiments on real-world underwater datasets demonstrate that our method achieves significant improvements in 3D reconstruction.
  arXiv  Detail & Related papers  (2025-05-27T14:37:58Z)
• 3D-UIR: 3D Gaussian for Underwater 3D Scene Reconstruction via Physics Based Appearance-Medium Decoupling [30.985414238960466]
  3D Gaussian Splatting (3DGS) offers real-time rendering capabilities, but struggles with underwater inhomogeneous environments.<n>We propose a physics-based framework that disentangles object appearance from water medium effects.<n>Our approach achieves both high-quality novel view synthesis and physically accurate scene restoration.
  arXiv  Detail & Related papers  (2025-05-27T14:19:30Z)
• Visual enhancement and 3D representation for underwater scenes: a review [13.809193345785388]
  Underwater visual enhancement (UVE) and underwater 3D reconstruction pose significant challenges in computer vision and AI-based tasks.<n>To advance research in these areas, we present an in-depth review from multiple perspectives.
  arXiv  Detail & Related papers  (2025-05-03T17:20:24Z)
• 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)
• Robust Geometry-Preserving Depth Estimation Using Differentiable Rendering [93.94371335579321]
  We propose a learning framework that trains models to predict geometry-preserving depth without requiring extra data or annotations. Comprehensive experiments underscore our framework's superior generalization capabilities. Our innovative loss functions empower the model to autonomously recover domain-specific scale-and-shift coefficients.
  arXiv  Detail & Related papers  (2023-09-18T12:36:39Z)
• Virtual Normal: Enforcing Geometric Constraints for Accurate and Robust Depth Prediction [87.08227378010874]
  We show the importance of the high-order 3D geometric constraints for depth prediction. By designing a loss term that enforces a simple geometric constraint, we significantly improve the accuracy and robustness of monocular depth estimation. We show state-of-the-art results of learning metric depth on NYU Depth-V2 and KITTI.
  arXiv  Detail & Related papers  (2021-03-07T00:08:21Z)
• Occlusion-Aware Depth Estimation with Adaptive Normal Constraints [85.44842683936471]
  We present a new learning-based method for multi-frame depth estimation from a color video. Our method outperforms the state-of-the-art in terms of depth estimation accuracy.
  arXiv  Detail & Related papers  (2020-04-02T07:10:45Z)

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.