RadarSFD: Single-Frame Diffusion with Pretrained Priors for Radar Point Clouds
For size-, weight-, and power-constrained robotic platforms, this work enables practical single-frame radar-based dense point cloud perception without requiring synthetic aperture or multi-frame aggregation.
RadarSFD reconstructs dense LiDAR-like point clouds from a single radar frame using a conditional latent diffusion model with pretrained priors, achieving state-of-the-art performance on the RadarHD benchmark and demonstrating strong generalization to new environments.
Millimeter-wave radar provides robust perception in fog, smoke, dust, and low light, making it attractive for size-, weight-, and power-constrained robotic platforms. Existing radar imaging methods typically rely on synthetic aperture or multi-frame aggregation to improve resolution, which is impractical for small aerial, inspection, or wearable systems. We present RadarSFD, a conditional latent diffusion framework that reconstructs dense LiDAR-like point clouds from a single radar frame without motion or SAR. Our approach transfers geometric priors from a pretrained monocular depth estimator into the diffusion backbone, anchors them to radar inputs via channel-wise latent concatenation, and regularizes outputs with a dual-space objective combining latent and pixel-space losses. On the RadarHD benchmark, RadarSFD achieves state-of-the-art performance against baseline models. Qualitative results show recovery of fine walls and narrow gaps, and experiments across new environments confirm strong generalization. Ablation studies highlight the importance of pretrained initialization, radar BEV conditioning, and the dual-space loss. Together, these results establish a practical single-frame, no-SAR mmWave radar pipeline for dense point cloud perception in compact robotic systems.