Lightweight Underwater Scene Reconstruction with Pose-Conditioned Neural Medium and 3D Gaussian Splatting

Parab, Shubham, Bian, Shaojun, Ihmeida, Mohamed and Zhang, Qichun (2026) Lightweight Underwater Scene Reconstruction with Pose-Conditioned Neural Medium and 3D Gaussian Splatting. In: 2026 31st International Conference on Automation and Computing (ICAC), 26-28 August 2026, High Wycombe, Buckinghamshire, United Kingdom.

Full text not available from this repository. (Request a copy)

Access this via: https://doi.org/10.1109/ICAC70325.2026.11712345

Abstract

Underwater 3D scene reconstruction is inherently challenging due to wavelength-dependent light absorption and scattering. SeaThru-NeRF integrates an underwater image-formation model into Neural Radiance Fields, achieving high-quality synthesis but suffering from prohibitively long training times and very low rendering throughput. 3D Gaussian Splatting (3DGS) trains in minutes and renders in real time, but lacks participating-medium modelling and produces colour distortion underwater. This work couples vanilla 3DGS with a lightweight, pose-conditioned neural medium. A compact multilayer perceptron, conditioned on camera position and view direction via sinusoidal positional encoding, predicts per-frame attenuation and backscatter coefficients that are applied as an image-space post-process, leaving the rasterisation loop unchanged. To stabilise joint optimisation, we introduce a deferred medium activation schedule and a progressive spherical-harmonics warm-up, supervised by a minimal three-term photometric loss. On the SeaThru-NeRF benchmark, the proposed method outperforms both SeaThru-NeRF and SeaSplat in PSNR, SSIM, and LPIPS averaged across four scenes, while training substantially faster than competing physics-aware approaches and rendering at real-time rates suitable for on-board AUV deployment.

Item Type:	Conference or Workshop Item (Paper)
Keywords:	underwater scene reconstruction,3D Gaussian Splatting,neural radiance fields, novel-view synthesis, autonomous underwater vehicles
Divisions:	College of Creative Arts, Technology and Engineering > Computing
Depositing User:	Jessie McLean
Date Deposited:	09 Nov 2026 17:02
Last Modified:	09 Nov 2026 17:02
URI:	https://bnu.repository.guildhe.ac.uk/id/eprint/21858

Actions (login required)

Edit Item