BRDF-NeRF: Neural Radiance Fields with Optical Satellite Images and BRDF Modelling

Ewelina Rupnik

Abstract:

Neural radiance fields (NeRF) have gained prominence as a machine learning technique for representing 3D scenes and estimating the bidirectional reflectance distribution function (BRDF) from multiple images. However, most existing research has focused on close-range imagery, typically modeling scene surfaces with simplified Microfacet BRDF models, which are often inadequate for representing complex Earth surfaces. Furthermore, NeRF approaches generally require large sets of simultaneously captured images -- a condition rarely met in satellite imaging.
To overcome these challenges, we introduce BRDF-NeRF, which incorporates the physically-based semi-empirical Rahman-Pinty-Verstraete (RPV) BRDF model, known to better capture the reflectance properties of natural surfaces. Additionally, we propose guided volumetric sampling and depth supervision to enable radiance field modeling with a minimal number of views. Our BRDF-NeRF successfully synthesizes novel views from unseen angles and generates high-quality digital surface models (DSMs) using three to four satellite images during training.