BathyFacto: Refraction-Aware Two-Media Neural Radiance Fields for Bathymetry
2026-05-11 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors developed BathyFacto, a method that improves 3D mapping of underwater areas using drone images by correcting how light bends at the water surface. Their system models the way light travels through air and water separately, using physics to better estimate depths. This approach produces much more accurate underwater point clouds compared to standard methods that ignore light bending. They also created tools to prepare data and convert results into usable formats for further analysis.
photogrammetryUAV imagerybathymetryrefractionStructure-from-MotionNerfactoSnell's lawpoint clouddensity fieldmulti-media modeling
Authors
Markus Brezovsky, Anatol Günthner, Frederik Schulte, Lukas Winiwarter, Boris Jutzi, Gottfried Mandlburger
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.