Underwater 3D Reconstruction

Follow this topic Ask about this topic

Underwater 3D reconstruction estimates the shape, appearance, and sometimes motion of submerged scenes for mapping, inspection, and scientific measurement, where refraction, light loss, backscatter, and turbidity complicate ordinary vision. Methods range from structure-from-motion and visual-inertial SLAM to learned depth and point maps, neural radiance fields, and Gaussian splatting; many now model water effects explicitly or fuse cameras with sonar, inertial sensors, and Doppler velocity logs. Evaluation uses underwater video and image benchmarks, sonar data, field surveys, and comparisons against registered acoustic or geometric measurements. A central tension is that models can produce convincing views in controlled settings yet remain unreliable for metric geometry in sparse, turbid, dynamically lit, or otherwise difficult real-world surveys.

Latest papers

38 papers6 papers in the last four weeks, up 50% on the four weeks before. 0.0% of all new papers.

Sonar-MASt3R: Real-Time Opti-Acoustic Fusion in Turbid, Unstructured Environments
Mar 13, 2026Amy Phung, Richard CamilliUnderwater 3D Reconstruction 3D Reconstruction
Applied Ocean Physics and Engineering, Woods Hole Oceanographic Institution, Deep Submergence Laboratory, Woods Hole, MA, USA · Massachusetts Institute of Technology, Cambridge, MA, USA
UD-SfPNet: An Underwater Descattering Shape-from-Polarization Network for 3D Normal Reconstruction
Mar 1, 2026Puyun Wang, Kaimin Yu, Huayang He +3Underwater 3D Reconstruction Surface Normal Estimation
Long-Term Multi-Session 3D Reconstruction Under Substantial Appearance Change
Feb 24, 2026Beverley Gorry, Tobias Fischer, Michael Milford +13D Reconstruction Structure from Motion
QUT Centre for Robotics School of Electrical Engineering and Robotics Queensland University of Technology Brisbane, QLD 4000, Australia
WaterClear-GS: Optical-Aware Gaussian Splatting for Underwater Reconstruction and Restoration
Jan 27, 2026Xinrui Zhang, Yufeng Wang, Zesheng Wang +33D Gaussian Splatting Underwater Image Enhancement
Beihang University
SurfSLAM: Sim-to-Real Underwater Stereo Reconstruction For Real-Time SLAM
Jan 15, 2026Onur Bagoren, Seth Isaacson, Sacchin Sundar +6Simultaneous Localization and Mapping Metric Depth Estimation
Department of Robotics, University of Michigan, Ann Arbor, MI 48109, USA
RUSplatting: Robust 3D Gaussian Splatting for Sparse-View Underwater Scene Reconstruction
May 21, 2025Zhuodong Jiang, Haoran Wang, Guoxi Huang +2Underwater 3D Reconstruction 3D Gaussian Splatting
Visual Information Laboratory, University of Bristol, Bristol, UK · Submerged Resources Center, National Park Service, Denver, CO, USA
Synthetic Enclosed Echoes: A New Dataset to Mitigate the Gap Between Simulated and Real-World Sonar Data
May 21, 2025Guilherme de Oliveira, Matheus M. dos Santos, Paulo L. J. Drews-JrSynthetic-to-Real Domain Adaptation Underwater Imaging
NAUTEC - Intelligent robotics and automation group, FURG - Federal University of Rio Grande, Rio Grande, RS, Brazil · ICMC - Institute of Mathematics and Computer Sciences, USP - University of S˜ao Paulo, S˜ao Carlos, SP, Brazil
TUGS: Physics-based Compact Representation of Underwater Scenes by Tensorized Gaussian
May 12, 2025Shijie Lian, Ziyi Zhang, Hua Li +43D Gaussian Splatting Underwater Imaging
1Huazhong University of Science and Technology · 2Zhongguancun Academy · 3The Chinese University of Hong Kong, Shenzhen +3

Mar 13, 2026J/K move · Enter open · S save

Sonar-MASt3R: Real-Time Opti-Acoustic Fusion in Turbid, Unstructured Environments

Amy Phung, Richard Camilli

Applied Ocean Physics and Engineering, Woods Hole Oceanographic Institution, Deep Submergence Laboratory, Woods Hole, MA, USA · Massachusetts Institute of Technology, Cambridge, MA, USA

Underwater 3D Reconstruction 3D Reconstruction Multimodal Sensor Fusion Underwater Imaging

Open paper AskPDF arXiv

Underwater intervention is an important capability in several marine domains, with numerous industrial, scientific, and defense applications. However, existing perception systems used during intervention operations rely on data from optical cameras, which limits capabilities in poor visibility or lighting conditions. Prior work has examined opti-acoustic fusion methods, which use sonar data to resolve the depth ambiguity of the camera data while using camera data to resolve the elevation angle ambiguity of the sonar data. However, existing methods cannot achieve dense 3D reconstructions in real-time, and few studies have reported results from applying these methods in a turbid environment. In this work, we propose the opti-acoustic fusion method Sonar-MASt3R, which uses MASt3R to extract dense correspondences from optical camera data in real-time and pairs it with geometric cues from an acoustic 3D reconstruction to ensure robustness in turbid conditions. Experimental results using data recorded from an opti-acoustic eye-in-hand configuration across turbidity values ranging from <0.5 to >12 NTU highlight this method's improved robustness to turbidity relative to baseline methods.