Multiview 3-D Surface Reconstruction From SAR Images by Inverse Rendering

The 3-D reconstruction of a scene from synthetic aperture radar (SAR) images mainly relies on interferometric measurements, which involve strict constraints on the acquisition process. These last years, progress in deep learning has significantly advanced 3-D reconstruction from multiple views in optical imaging, mainly through reconstruction-by-synthesis approaches popularized by neural radiance fields (NeRFs). In this article, we propose a new inverse rendering method for 3-D reconstruction from a few incoherent SAR views, drawing inspiration from optical approaches. First, we introduce a new simplified differentiable SAR rendering model, able to synthetize images from a digital surface model (DSM) and a radar backscattering coefficients map. Then, we introduce a coarse-to-fine strategy to reconstruct the DSM and the map of backscattering coefficients of an SAR scene starting only from a few SAR views. We use a neural field, i.e., a continuous parametric model based on a multilayer perceptron, to represent the SAR scene. Finally, we present preliminary results of DSM reconstruction from synthetic SAR images produced by ONERA’s physically based EMPRISE simulator, supporting the potential of applying inverse rendering approaches to SAR data to efficiently exploit geometric disparities in future applications such as multisensor data fusion.