The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Download
Share
Publications Copernicus
Download
Citation
Share
Articles | Volume XLVIII-2/W10-2025
https://doi.org/10.5194/isprs-archives-XLVIII-2-W10-2025-39-2025
https://doi.org/10.5194/isprs-archives-XLVIII-2-W10-2025-39-2025
07 Jul 2025
 | 07 Jul 2025

Analysis of refraction aware Neural Radiance Fields for 3D reconstruction of through the water scenes

Markus Brezovsky, Anatol Günthner, Frederik Schulte, Lukas Winiwarter, Boris Jutzi, and Gottfried Mandlburger

Keywords: NeRFrac, Underwater Photogrammetry, Neural Radiance Fields, Bathymetry, UAV Imaging, Refraction Correction

Abstract. Neural Radiance Fields (NeRFs) synthesize novel views based on images acquired from different camera positions to represent 3D scenes. However, since they assume linear light paths, they are unsuitable for underwater environments where refraction causes nonlinear ray trajectories, resulting in blurred scene reconstructions due to the absence of physical light path modeling. Developments, such as NeRFrac, try to explicitly model refractive surfaces by incorporating Snell’s law into NeRF frameworks. Nevertheless, the predominant objective within the computer vision community, the generation of high-quality renderings, assessed through metrics, e.g. including the Peak Signal-to-Noise Ratio (PSNR) persists. However, the main task in photogrammetric and geospatial applications is geometric reconstruction in the form of 3D point clouds. Therefore, this work investigates the possibilities of extracting 3D point clouds from refraction-aware NeRF implementations, specifically evaluating the NeRFrac codebase with the use of nine images.

Share