Radon Implicit Field Transform: Fully Radar-Native Novel-View Synthesis and 3D Reconstruction

We introduce the Radon Implicit Field Transform (RIFT), a fully radar-native framework for complex-valued novel-view synthesis and 3D reconstruction that combines an adaptive point-scatterer representation with a radar forward model. Both initialization and optimization use only complex radar measurements and calibrated sensor poses, without visual or LiDAR-derived priors, initialization, or supervision. RIFT represents the scene with point scatterers at adaptive spatial resolutions, with learnable positions and direction-dependent complex reflectance parameterized by spherical harmonics. We incorporate the generalized Radon transform as a forward model and optimize point-scatterer positions and reflectance by matching predicted and measured complex radar signals. During optimization, signal-loss gradients guide local increases in spatial resolution and spherical-harmonic expansion degree; these capacity updates leave the current signal predictions unchanged, except for the coarse-to-fine densification we use on lower-resolution measured radar data. We evaluate complex-valued novel-view synthesis by comparing forward-model predictions at unseen sensor poses with held-out complex measurements, and evaluate 3D reconstruction by comparing geometry extracted from the learned point scatterers with ground-truth scene geometry. On our simulated dataset, RIFT achieves a mean held-out complex relative mean-squared error of $0.3909$ and a mean symmetric squared Chamfer distance of $$\begin{gathered} 4.813 \\ times10^{-5} \\ , \\ mathrm{m}^2 \end{gathered}$$;on a real-world dataset, it reduces the symmetric squared Chamfer distance by up to $95.12$ relative to the strongest baseline, reaching $$\begin{gathered} 5.536\times 10^{-2} \\ , \\ mathrm{m}^2 \end{gathered}$$.