# Real-Time Dense 3D Mapping of Underwater Environments

arXiv: https://arxiv.org/abs/2304.02704 · HTML: https://mlsanity.com/paper/2304.02704/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 54 references that are in the map.
- First posted on arXiv 5 Apr 2023.

## Builds on (most cited first, 12 of 12)

- [NeuralRecon: Real-Time Coherent 3D Reconstruction from Monocular Video](https://mlsanity.com/paper/2104.00681/) (2021)
- [Neural RGB->D Sensing: Depth and Uncertainty from a Video Camera](https://mlsanity.com/paper/1901.02571/) (2019)
- [DeepVideoMVS: Multi-View Stereo on Video with Recurrent Spatio-Temporal Fusion](https://mlsanity.com/paper/2012.02177/) (2020)
- [Multi-view Depth Estimation using Epipolar Spatio-Temporal Networks](https://mlsanity.com/paper/2011.13118/) (2020)
- [Video Depth Estimation by Fusing Flow-to-Depth Proposals](https://mlsanity.com/paper/1912.12874/) (2019)
- [SVIn2: An Underwater SLAM System using Sonar, Visual, Inertial, and Depth Sensor](https://mlsanity.com/paper/1810.03200/) (2018)
- [Experimental Comparison of Open Source Visual-Inertial-Based State Estimation Algorithms in the Underwater Domain](https://mlsanity.com/paper/1904.02215/) (2019)
- [Navigation in the Presence of Obstacles for an Agile Autonomous Underwater Vehicle](https://mlsanity.com/paper/1903.11750/) (2019)
- [VOLDOR-SLAM: For the Times When Feature-Based or Direct Methods Are Not Good Enough](https://mlsanity.com/paper/2104.06800/) (2021)
- [High Definition, Inexpensive, Underwater Mapping](https://mlsanity.com/paper/2203.05640/) (2022)
- [AquaVis: A Perception-Aware Autonomous Navigation Framework for Underwater Vehicles](https://mlsanity.com/paper/2110.01646/) (2021)
- [Real-time Model-based Image Color Correction for Underwater Robots](https://mlsanity.com/paper/1904.06437/) (2019)

## Built on by (most cited first, 16 of 16)

- [CVRecon: Rethinking 3D Geometric Feature Learning For Neural Reconstruction](https://mlsanity.com/paper/2304.14633/) (2023)
- [Enhancing Multi-Hop Knowledge Graph Reasoning through Reward Shaping Techniques](https://mlsanity.com/paper/2403.05801/) (2024)
- [Aquatic-GS: A Hybrid 3D Representation for Underwater Scenes](https://mlsanity.com/paper/2411.00239/) (2024)
- [CaveSeg: Deep Semantic Segmentation and Scene Parsing for Autonomous Underwater Cave Exploration](https://mlsanity.com/paper/2309.11038/) (2023)
- [3D-UIR: 3D Gaussian for Underwater 3D Scene Reconstruction via Physics Based Appearance-Medium Decoupling](https://mlsanity.com/paper/2505.21238/) (2025)
- [Image-Based Relocalization and Alignment for Long-Term Monitoring of Dynamic Underwater Environments](https://mlsanity.com/paper/2503.04096/) (2025)
- [UVLM: Benchmarking Video Language Model for Underwater World Understanding](https://mlsanity.com/paper/2507.02373/) (2025)
- [Visual SLAM with 3D Gaussian Primitives and Depth Priors Enabling Novel View Synthesis](https://mlsanity.com/paper/2408.05635/) (2024)
- [PUGS: Perceptual Uncertainty for Grasp Selection in Underwater Environments](https://mlsanity.com/paper/2502.09824/) (2025)
- [Improving Neural Indoor Surface Reconstruction with Mask-Guided Adaptive Consistency Constraints](https://mlsanity.com/paper/2309.09739/) (2023)
- [Swimm3R: Splatting with Medium-aware SfM for Underwater 3D Reconstruction](https://mlsanity.com/paper/2608.00950/) (2026)
- [Long-Term Multi-Session 3D Reconstruction Under Substantial Appearance Change](https://mlsanity.com/paper/2602.20584/) (2026)
- [ReefMapGS: Enabling Large-Scale Underwater Reconstruction by Closing the Loop Between Multimodal SLAM and Gaussian Splatting](https://mlsanity.com/paper/2604.11992/) (2026)
- [Semantically-Aware Diver Activity Recognition Framework for Effective Underwater Multi-Human-Robot Collaboration](https://mlsanity.com/paper/2606.12374/) (2026)
- [AquaFlow: A Monocular Gaussian Splatting SLAM for Underwater Streaming Reconstruction](https://mlsanity.com/paper/2608.22906/) (2026)
- [BenthicFlow: Generating Extensible Underwater Environments via Flow Matching](https://mlsanity.com/paper/2608.23173/) (2026)

## Abstract (arXiv)

This paper addresses real-time dense 3D reconstruction for a resource-constrained Autonomous Underwater Vehicle (AUV). Underwater vision-guided operations are among the most challenging as they combine 3D motion in the presence of external forces, limited visibility, and absence of global positioning. Obstacle avoidance and effective path planning require online dense reconstructions of the environment. Autonomous operation is central to environmental monitoring, marine archaeology, resource utilization, and underwater cave exploration. To address this problem, we propose to use SVIn2, a robust VIO method, together with a real-time 3D reconstruction pipeline. We provide extensive evaluation on four challenging underwater datasets. Our pipeline produces comparable reconstruction with that of COLMAP, the state-of-the-art offline 3D reconstruction method, at high frame rates on a single CPU.