Initial Experiments on the Use of Radiance Fields for Underwater 3D Reconstruction

Underwater photogrammetry presents unique challenges, including light attenuation, refraction, and turbidity, that affect theaccuracy and quality of 3D reconstructions. This study investigates the performance of novel neural rendering techniques, NeuralRadiance Fields (NeRF), SeaThru-NeRF, and 3D Gaussian Splatting (3DGS), in comparison to conventional Structure-from-Motion(SfM) workflows. Using a dataset acquired during the SIFET benchmark campaign on a submerged Roman archaeological site, weprocessed image data via Nerfacto, SeaThru, and Jawset Postshot (3DGS) and compared outputs against a reference model producedin Agisoft Metashape. Evaluation criteria included processing time, geometric accuracy (via M3C2 analysis), point cloud density androughness, and point cloud completeness. Results show that radiance fields-based methods significantly reduce processing timewhile providing competitive visual results. SeaThru-NeRF demonstrated the highest geometric accuracy, benefiting fromunderwater-specific corrections, while 3DGS offered photorealistic rendering. These findings highlight the potential of neuralmethods for underwater cultural heritage documentation, though further improvements are needed in data fidelity and robustnessunder challenging underwater conditions.