BathyFacto: Refraction-Aware Two-Media Neural Radiance Fields for Bathymetry

TL;DR

BathyFacto is a refraction-aware neural radiance field extension that improves underwater bathymetry accuracy by modeling light refraction at the air-water interface using a two-media approach.

Contribution

It introduces a novel two-media extension of Nerfacto that explicitly models refraction for precise underwater 3D reconstruction from UAV imagery.

Findings

Achieves a mean distance of 0.06 m in simulated scenes, outperforming baselines.

Provides 87% completeness in underwater point cloud reconstruction.

Extends point cloud export with refraction correction and coordinate transforms.

Abstract

Through-water photogrammetry based on UAV imagery enables shallow-water bathymetry, but refraction at the air-water interface violates the straight-ray assumption of Structure-from-Motion and causes systematic depth bias. We present BathyFacto, a refraction-aware two-media extension of Nerfacto integrated into Nerfstudio that targets metrically precise underwater point clouds. BathyFacto uses a shared hash-grid-based density field with a medium-conditioned color head that receives a one-bit medium flag (air or water) and traces each camera ray as two segments: a straight segment in air up to a planar water surface and a refracted segment in water computed via Snell's law with known refractive indices. To allocate samples efficiently across the air-water boundary, we employ a single proposal-network sampler that operates on a virtual straight ray spanning both media, combined with a kinked density wrapper that transparently corrects water-segment positions along the refracted direction before density evaluation. A data adaptation pipeline converts photogrammetric reconstructions to a Nerfstudio-compatible format, estimates the water plane from boundary markers, and provides per-pixel medium masks to gate refraction. We also extend the point cloud export with refraction-corrected backprojection and reversible coordinate transforms to world and global frames. On a simulated two-media scene with known ground truth, BathyFacto with refraction achieves a Cloud-to-Mesh mean distance of 0.06 m and 87 % completeness, compared to 0.52 m / 29 % for the Nerfacto baseline and 0.36 m / 21% for conventional MVS without refraction correction.