Revisiting Radar Perception With Spectral Point Clouds
2026-04-09 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors explore different ways to process radar data for perception models, comparing dense radar spectra to sparse point clouds. They introduce the idea of 'spectral point clouds,' which add spectral info to point clouds to make them more reliable and less dependent on specific sensors. Their experiments show that enriched point clouds can perform just as well, or even better, than traditional dense radar spectra. This suggests that point clouds could be a better, more flexible way to use radar data in future models.
radar perceptionrange-Doppler spectrapoint cloudsspectral enrichmentsensor transferabilityradar data representationsparse vs dense dataradar foundation models
Authors
Hamza Alsharif, Jing Gu, Pavol Jancura, Satish Ravindran, Gijs Dubbelman
Abstract
Radar perception models are trained with different inputs, from range-Doppler spectra to sparse point clouds. Dense spectra are assumed to outperform sparse point clouds, yet they can vary considerably across sensors and configurations, which hinders transfer. In this paper, we provide alternatives for incorporating spectral information into radar point clouds and show that, point clouds need not underperform compared to spectra. We introduce the spectral point cloud paradigm, where point clouds are treated as sparse, compressed representations of the radar spectra, and argue that, when enriched with spectral information, they serve as strong candidates for a unified input representation that is more robust against sensor-specific differences. We develop an experimental framework that compares spectral point cloud (PC) models at varying densities against a dense range-Doppler (RD) benchmark, and report the density levels where the PC configurations meet the performance of the RD benchmark. Furthermore, we experiment with two basic spectral enrichment approaches, that inject additional target-relevant information into the point clouds. Contrary to the common belief that the dense RD approach is superior, we show that point clouds can do just as well, and can surpass the RD benchmark when enrichment is applied. Spectral point clouds can therefore serve as strong candidates for unified radar perception, paving the way for future radar foundation models.