SurfSLAM: Sim-to-Real Underwater Stereo Reconstruction For Real-Time SLAM

• URL: http://arxiv.org/abs/2601.10814v2
• Date: Tue, 20 Jan 2026 22:55:23 GMT
• Title: SurfSLAM: Sim-to-Real Underwater Stereo Reconstruction For Real-Time SLAM
• Abstract summary: In underwater environments, images are degraded by light attenuation, visual artifacts, and dynamic lighting conditions.<n>As a result, stereo estimation networks trained on in-air data cannot transfer directly to the underwater domain.<n>We propose a novel framework that enables sim-to-real training of underwater stereo disparity estimation networks using simulated data.
• Score: 17.714335268428595
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Localization and mapping are core perceptual capabilities for underwater robots. Stereo cameras provide a low-cost means of directly estimating metric depth to support these tasks. However, despite recent advances in stereo depth estimation on land, computing depth from image pairs in underwater scenes remains challenging. In underwater environments, images are degraded by light attenuation, visual artifacts, and dynamic lighting conditions. Furthermore, real-world underwater scenes frequently lack rich texture useful for stereo depth estimation and 3D reconstruction. As a result, stereo estimation networks trained on in-air data cannot transfer directly to the underwater domain. In addition, there is a lack of real-world underwater stereo datasets for supervised training of neural networks. Poor underwater depth estimation is compounded in stereo-based Simultaneous Localization and Mapping (SLAM) algorithms, making it a fundamental challenge for underwater robot perception. To address these challenges, we propose a novel framework that enables sim-to-real training of underwater stereo disparity estimation networks using simulated data and self-supervised finetuning. We leverage our learned depth predictions to develop SurfSLAM, a novel framework for real-time underwater SLAM that fuses stereo cameras with IMU, barometric, and Doppler Velocity Log (DVL) measurements. Lastly, we collect a challenging real-world dataset of shipwreck surveys using an underwater robot. Our dataset features over 24,000 stereo pairs, along with high-quality, dense photogrammetry models and reference trajectories for evaluation. Through extensive experiments, we demonstrate the advantages of the proposed training approach on real-world data for improving stereo estimation in the underwater domain and for enabling accurate trajectory estimation and 3D reconstruction of complex shipwreck sites.

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: 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)
• 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)
• NAUTILUS: A Large Multimodal Model for Underwater Scene Understanding [60.76337064425815]
  We study the underwater scene understanding methods, which aim to achieve automated underwater exploration.<n>NautData is a dataset containing 1.45 M image-text pairs supporting eight underwater scene understanding tasks.<n>We propose a plug-and-play vision feature enhancement (VFE) module, which explicitly restores clear underwater information.
  arXiv  Detail & Related papers  (2025-10-31T14:00:35Z)
• DUViN: Diffusion-Based Underwater Visual Navigation via Knowledge-Transferred Depth Features [47.88998580611257]
  We propose a Diffusion-based Underwater Visual Navigation policy via knowledge-transferred depth features, named DUViN.<n>DuViN guides the vehicle to avoid obstacles and maintain a safe and perception awareness altitude relative to the terrain without relying on pre-built maps.<n> Experiments in both simulated and real-world underwater environments demonstrate the effectiveness and generalization of our approach.
  arXiv  Detail & Related papers  (2025-09-03T03:43:12Z)
• Manipulation as in Simulation: Enabling Accurate Geometry Perception in Robots [55.43376513158555]
  Camera Depth Models (CDMs) are a simple plugin on daily-use depth cameras.<n>We develop a neural data engine that generates high-quality paired data from simulation by modeling a depth camera's noise pattern.<n>For the first time, our experiments demonstrate, for the first time, that a policy trained on raw simulated depth, without the need for adding noise or real-world fine-tuning, generalizes seamlessly to real-world robots.
  arXiv  Detail & Related papers  (2025-09-02T17:29:38Z)
• Towards Training-Free Underwater 3D Object Detection from Sonar Point Clouds: A Comparison of Traditional and Deep Learning Approaches [0.0]
  We develop and compare two paradigms for training-free detection of artificial structures in multibeam echo-sounder point clouds.<n>Our dual approach combines a physics-based sonar simulation pipeline that generates synthetic training data for state-of-the-art neural networks, with a robust model-based template matching system.<n>Our findings challenge conventional wisdom about data-hungry deep learning in underwater domains and establish the first large-scale benchmark for training-free underwater 3D detection.
  arXiv  Detail & Related papers  (2025-08-22T12:08:21Z)
• 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)
• FAFA: Frequency-Aware Flow-Aided Self-Supervision for Underwater Object Pose Estimation [65.01601309903971]
  We introduce FAFA, a Frequency-Aware Flow-Aided self-supervised framework for 6D pose estimation of unmanned underwater vehicles (UUVs) Our framework relies solely on the 3D model and RGB images, alleviating the need for any real pose annotations or other-modality data like depths. We evaluate the effectiveness of FAFA on common underwater object pose benchmarks and showcase significant performance improvements compared to state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-09-25T03:54:01Z)
• Atlantis: Enabling Underwater Depth Estimation with Stable Diffusion [30.122666238416716]
  We propose a novel pipeline for generating underwater images using accurate terrestrial depth data. This approach facilitates the training of supervised models for underwater depth estimation. We introduce a unique Depth2Underwater ControlNet, trained on specially prepared Underwater, Depth, Text data triplets.
  arXiv  Detail & Related papers  (2023-12-19T08:56:33Z)
• FLSea: Underwater Visual-Inertial and Stereo-Vision Forward-Looking Datasets [8.830479021890575]
  We have collected underwater forward-looking stereo-vision and visual-inertial image sets in the Mediterranean and Red Sea. These datasets are critical for the development of several underwater applications, including obstacle avoidance, visual odometry, 3D tracking, Simultaneous localization and Mapping (SLAM) and depth estimation.
  arXiv  Detail & Related papers  (2023-02-24T17:39:53Z)
• Neural Scene Representation for Locomotion on Structured Terrain [56.48607865960868]
  We propose a learning-based method to reconstruct the local terrain for a mobile robot traversing urban environments. Using a stream of depth measurements from the onboard cameras and the robot's trajectory, the estimates the topography in the robot's vicinity. We propose a 3D reconstruction model that faithfully reconstructs the scene, despite the noisy measurements and large amounts of missing data coming from the blind spots of the camera arrangement.
  arXiv  Detail & Related papers  (2022-06-16T10:45:17Z)
• Self-Supervised Depth Completion for Active Stereo [55.79929735390945]
  Active stereo systems are widely used in the robotics industry due to their low cost and high quality depth maps. These depth sensors suffer from stereo artefacts and do not provide dense depth estimates. We present the first self-supervised depth completion method for active stereo systems that predicts accurate dense depth maps.
  arXiv  Detail & Related papers  (2021-10-07T07:33:52Z)

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.