Underwater 3D Scene Reconstruction Using Neural Rendering: A Survey with Emphasis on 3D Gaussian Splatting Framework
Parab, Shubham, Bian, Shaojun, Wu, Yun and Tharib, Safa (2026) Underwater 3D Scene Reconstruction Using Neural Rendering: A Survey with Emphasis on 3D Gaussian Splatting Framework. In: 2026 12th International Conference on Virtual Reality (ICVR), Cardiff, United Kingdom.
|
Text
Tharib_21793.pdf - Published Version Available under License Creative Commons Attribution Non-commercial. Download (184kB) | Preview |
Abstract
Underwater 3D reconstruction is crucial for autonomous underwater vehicles (AUVs) and marine surveys but is more challenging than terrestrial scenarios due to attenuation, backscatter, and uneven lighting. While traditional photogrammetric pipelines fail to mitigate such effects, recent Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS) are promising, however, still break down similarly when applied directly to underwater imagery, as both assume a transparent propagation medium. This survey provides a structured review of methods that adapt NeRF and 3DGS specifically for underwater 3D reconstruction. By formalising the underwater image formation model for specific architectural options, we introduce a novel taxonomy of four adaptation strategies based on physical model integration, distractor and dynamic scene handling, depth and geometry-focused design, and sparse-view robustness. Furthermore, NeRF and 3DGS-based methods are evaluated on benchmark datasets and quantitatively compared using standard metrics, including PSNR, SSIM, and LPIPS. Therefore, we identify the open challenges covering forward scattering, unified benchmarking, dynamic scenes, sparse-view robustness, water-type generalisation, foundation model integration, real-time deployment, GS-SLAM, 3D foundation model priors, and multimodal sensing fusion. To our best knowledge, this survey is among the first dedicated, taxonomy-driven, equation-level surveys of underwater 3DGS methods, including recent approaches such as OceanSplat and RUSplatting, which were absent from prior reviews.
| Item Type: | Conference or Workshop Item (Paper) |
|---|---|
| Divisions: | College of Creative Arts, Technology and Engineering |
| Depositing User: | Jessie McLean |
| Date Deposited: | 05 Oct 2026 14:33 |
| Last Modified: | 05 Oct 2026 14:42 |
| URI: | https://bnu.repository.guildhe.ac.uk/id/eprint/21793 |
Actions (login required)
 |
Edit Item |