UW-GS: Distractor-Aware 3D Gaussian Splatting for Enhanced Underwater Scene Reconstruction
About
3D Gaussian splatting (3DGS) offers the capability to achieve real-time high quality 3D scene rendering. However, 3DGS assumes that the scene is in a clear medium environment and struggles to generate satisfactory representations in underwater scenes, where light absorption and scattering are prevalent and moving objects are involved. To overcome these, we introduce a novel Gaussian Splatting-based method, UW-GS, designed specifically for underwater applications. It introduces a color appearance that models distance-dependent color variation, employs a new physics-based density control strategy to enhance clarity for distant objects, and uses a binary motion mask to handle dynamic content. Optimized with a well-designed loss function supporting for scattering media and strengthened by pseudo-depth maps, UW-GS outperforms existing methods with PSNR gains up to 1.26dB. To fully verify the effectiveness of the model, we also developed a new underwater dataset, S-UW, with dynamic object masks.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Underwater 3D Scene Reconstruction | SeaThru-NeRF Panama | PSNR31.36 | 7 | |
| Underwater 3D Scene Reconstruction | SeaThru-NeRF IUI3 Red Sea | PSNR27.06 | 7 | |
| Underwater 3D Scene Reconstruction | SeaThru-NeRF Curacao | PSNR27.62 | 7 | |
| Underwater 3D Scene Reconstruction | SeaThru-NeRF J.G. Red Sea | PSNR20.05 | 7 |