Enhanced WaterSplatting for underwater 3D reconstruction based on progressive perceptual loss and spatial coordinate encoding

Abstract

Abstract. Underwater three-dimensional reconstruction is inherently challenged by light scattering and wavelength-dependent absorption, causing color distortion, contrast degradation, and limited visibility in recovered geometries. Existing underwater three-dimensional (3D) Gaussian splatting methods rely solely on pixel-wise losses [L1/structural similarity index measure (SSIM)], which produce over-smoothed textures in scattering environments, while their direction-only medium modeling assumes spatially homogeneous water properties that contradict real-world depth-dependent turbidity. To address these limitations, we present an enhanced framework for underwater 3D reconstruction integrating progressive perceptual supervision with spatial coordinate encoding. A progressively weighted learned perceptual image patch similarity (LPIPS) loss recovers fine texture details without compromising geometric accuracy, while sinusoidal pixel-coordinate encoding enables self-supervised modeling of spatially varying turbidity without depth sensors. Experimental evaluation on the SeaThru-NeRF dataset demonstrates substantial perceptual quality improvements, with the progressive LPIPS alone achieving up to 33.9% LPIPS reduction on high-turbidity scenes, while the full framework maintains photometric accuracy (peak signal-to-noise ratio/SSIM). Cross-dataset evaluation on the out-of-distribution, deep-sea Submerged3D dataset further confirms that these perceptual gains generalize beyond a single benchmark. The method achieves interactive rendering performance (15 to 35 frames per second) and efficient training (∼8 to 13 min), providing a practical solution for real-time underwater 3D reconstruction in robotic applications.