Multi-view 3D surface reconstruction from SAR images by inverse rendering

TL;DR

This paper introduces a novel inverse rendering approach for 3D surface reconstruction from SAR images, leveraging a differentiable SAR model and deep learning to enable reconstruction from unconstrained multi-view SAR data.

Contribution

It presents a new differentiable SAR rendering model and a coarse-to-fine training strategy for MLPs, advancing 3D reconstruction from SAR images beyond traditional interferometric methods.

Findings

Effective reconstruction demonstrated on synthetic SAR data

Potential for multi-sensor data fusion in SAR imaging

Exploits geometric disparities in SAR images

Abstract

3D 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 3D reconstruction from multiple views in optical imaging, mainly through reconstruction-by-synthesis approaches pioneered by Neural Radiance Fields. In this paper, we propose a new inverse rendering method for 3D reconstruction from unconstrained SAR images, drawing inspiration from optical approaches. First, we introduce a new simplified differentiable SAR rendering model, able to synthesize images from a digital elevation model and a radar backscattering coefficients map. Then, we introduce a coarse-to-fine strategy to train a Multi-Layer Perceptron (MLP) to fit the height and appearance of a given radar scene from a few SAR views. Finally, we demonstrate the surface reconstruction capabilities of our method on synthetic SAR images produced by ONERA's physically-based EMPRISE simulator. Our method showcases the potential of exploiting geometric disparities in SAR images and paves the way for multi-sensor data fusion.