Radar Fields: Frequency-Space Neural Scene Representations for FMCW Radar

TL;DR

This paper introduces Radar Fields, a neural scene reconstruction method for FMCW radar that models scenes in Fourier frequency space, enabling effective outdoor scene synthesis and occupancy extraction without volume rendering.

Contribution

The paper presents a novel neural scene representation for radar data that combines physics-informed sensor modeling with neural geometry, specifically designed for active radar imagers.

Findings

Effective reconstruction in diverse outdoor scenarios

Robust performance in harsh weather conditions

No reliance on volume rendering, using Fourier space learning

Abstract

Neural fields have been broadly investigated as scene representations for the reproduction and novel generation of diverse outdoor scenes, including those autonomous vehicles and robots must handle. While successful approaches for RGB and LiDAR data exist, neural reconstruction methods for radar as a sensing modality have been largely unexplored. Operating at millimeter wavelengths, radar sensors are robust to scattering in fog and rain, and, as such, offer a complementary modality to active and passive optical sensing techniques. Moreover, existing radar sensors are highly cost-effective and deployed broadly in robots and vehicles that operate outdoors. We introduce Radar Fields - a neural scene reconstruction method designed for active radar imagers. Our approach unites an explicit, physics-informed sensor model with an implicit neural geometry and reflectance model to directly synthesize raw radar measurements and extract scene occupancy. The proposed method does not rely on volume rendering. Instead, we learn fields in Fourier frequency space, supervised with raw radar data. We validate the effectiveness of the method across diverse outdoor scenarios, including urban scenes with dense vehicles and infrastructure, and in harsh weather scenarios, where mm-wavelength sensing is especially favorable.