SOURCE-LINKED INTELLIGENCE

3D Point Splatting for mmWave Radar Novel View Synthesis

arXiv · AI, language, vision and robotics · article · Sep 10, 2026 · UTC

Solving novel view synthesis (NVS) for millimeter-wave (mmWave) radar requires a renderer that is physically faithful, complex-valued, and multi-viewpoint-tractable. No prior method achieves these three properties simultaneously. Differentiable Monte Carlo (MC) ray tracers implement the radar forward model directly with explicit material modeling and complex outputs, but do not scale to the multi-view optimization NVS demands. Optical-NVS ports of NeRF, hash grids, and 3D Gaussians train fast but discard phase and replace explicit material modeling with opaque learned features, restricting the

Read original source ↗ Open in workspace

recordType

paper

region

Global