Diffusion-Based mmWave Radar Point Cloud Enhancement Driven by Range Images

Millimeter-wave (mmWave) radar has attracted significant attention in robotics and autonomous driving due to its robustness in harsh environments. However, the radar point clouds are typically sparse and noisy, which limits its futher development. Traditional mmWave radar enhancement approaches often struggle to leverage the effectiveness of diffusion models in super-resolution, largely due to the unnatural range-azimuth heatmap (RAH) or bird's eye view (BEV) representation. To address this issue, we pioneer the integration of range image representations into an image diffusion framework that leverages pre-trained image diffusion priors to generate dense and accurate 3D mmWave radar point clouds with LiDAR-like quality. Extensive evaluations on both public datasets and self-constructed datasets demonstrate that our approach provides substantial improvements, establishing a new state-of-the-art performance in generating truly three-dimensional LiDAR-like point clouds via mmWave radar.