AquaFlow: A Monocular Gaussian Splatting SLAM for Underwater Streaming Reconstruction
2026-08-24 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors developed AquaFlow, a new method for creating 3D models of underwater scenes using just one camera. Underwater images are hard to work with because water affects light and distorts the view, making it tough to track the camera and build accurate models. AquaFlow improves this by training on lots of underwater data and using a special technique to better represent how light behaves underwater. Tests show AquaFlow is more accurate and produces clearer 3D reconstructions than previous methods.
3D Gaussian SplattingMonocular reconstructionUnderwater imagingCamera pose trackingLight attenuationScatteringNeural GaussiansOptical modelStreaming mappingPSNR
Authors
Yingxiang Xu, Kerui Ren, Wenqi Guo, Changjian Jiang, Tao Lu, Linning Xu, Mulin Yu
Abstract
Recent monocular 3D Gaussian Splatting (3DGS) streaming reconstruction methods have achieved impressive performance by balancing reconstruction quality and efficiency. However, extending these frameworks to underwater scenes remains challenging due to severe visual degradation, such as light attenuation and scattering, which degrades camera pose tracking and distorts scene geometry. To address these challenges, we propose AquaFlow, a monocular Gaussian Splatting streaming reconstruction framework for efficient and high-fidelity underwater reconstruction. Specifically, AquaFlow fine-tunes a 3D vision foundation model on large-scale underwater data for robust pose and pointmap estimation, and introduces a medium-guided incremental Gaussian initialization strategy for streaming mapping. Furthermore, we develop a streaming-compatible hybrid scene representation that integrates structured, distance-conditioned neural Gaussians with a physics-inspired optical model to compensate for underwater image formation effects, enabling accurate scene reconstruction. We evaluate AquaFlow on a comprehensive dataset of 62 diverse underwater trajectories, collected from both public benchmarks and in-the-wild web videos across various scales. Extensive experiments demonstrate that AquaFlow achieves state-of-the-art tracking and rendering performance, reducing average localization error by 13.2% and improving PSNR by 4.74 dB compared to WaterSplat-SLAM.