BathyFacto modifies Nerfacto to trace refracted rays through air and water using Snell's law and a kinked density wrapper, achieving 0.06 m Cloud-to-Mesh distance and 87% completeness on simulated bathymetry data versus 0.52 m and 29% for the baseline.
Multi-view stereo: A tutorial,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
An adaptive multi-criteria feature selection policy for 3D scene reconstruction that outperforms random, texture-only, and uniform-grid baselines on synthetic multi-view tests for completeness and RMSE.
citing papers explorer
-
BathyFacto: Refraction-Aware Two-Media Neural Radiance Fields for Bathymetry
BathyFacto modifies Nerfacto to trace refracted rays through air and water using Snell's law and a kinked density wrapper, achieving 0.06 m Cloud-to-Mesh distance and 87% completeness on simulated bathymetry data versus 0.52 m and 29% for the baseline.
-
Feature-Optimized Vision for Adaptive 3D Scene Reconstruction
An adaptive multi-criteria feature selection policy for 3D scene reconstruction that outperforms random, texture-only, and uniform-grid baselines on synthetic multi-view tests for completeness and RMSE.