DART — Doppler Aided Radar Tomography, a Neural Radiance Field-inspired approach to radar novel view synthesis using implicit neural inverse imaging

Anthony Rowe

Abstract: Simulation is an invaluable tool for radio-frequency system designers that enables rapid prototyping of vari- ous algorithms for imaging, target detection, classifica- tion, and tracking. However, simulating realistic radar scans is a challenging task that requires an accurate model of the scene, radio frequency material properties, and a corresponding radar synthesis function. Rather than specifying these models explicitly, we propose DART — Doppler Aided Radar Tomography, a Neural Radiance Field-inspired method which uses radar-specific physics to create a reflectance and transmittance-based rendering pipeline for range-Doppler images. We then evaluate DART by constructing a custom data collection platform and col- lecting a novel radar dataset together with accurate posi- tion and instantaneous velocity measurements from lidar- based localization. In comparison to state-of-the-art base- lines, DART synthesizes superior radar range-Doppler im- ages from novel views across all datasets and additionally can be used to generate high quality tomographic images.