R2LDM: An Efficient 4D Radar Super-Resolution Framework Leveraging Diffusion Model

We introduce R2LDM, an innovative approach for generating dense and accurate 4D radar point clouds, guided by corresponding LiDAR point clouds. Instead of utilizing range images or bird’s eye view (BEV) images, we represent both LiDAR and 4D radar point clouds using voxel features, which more effectively capture 3D shape information. Subsequently, we propose the Latent Voxel Diffusion Model (LVDM), which performs the diffusion process in the latent space. Additionally, a novel Latent Point Cloud Reconstruction (LPCR) module is utilized to reconstruct point clouds from high-dimensional latent voxel features. As a result, R2LDM effectively generates LiDAR-like point clouds from paired raw radar data. We evaluate our approach on two different datasets, and the experimental results demonstrate that our model achieves 6- to 10-fold densification of radar point clouds, outperforming state-of-the-art baselines in 4D radar point cloud super-resolution. Furthermore, the enhanced radar point clouds generated by our method significantly improve downstream tasks, achieving up to 31. 7% improvement in point cloud registration recall rate and 24. 9% improvement in object detection accuracy.

Authors

• Boyuan Zheng
• Shouyi Lu
• Renbo Huang
• Minqing Huang
• Fan Lu
• Wei Tian 0001
• Guirong Zhuo
• Lu Xiong 0001

Keywords

• Point cloud compression
• Radar cross-sections
• Laser radar
• Three-dimensional displays
• Superresolution
• Radar
• Object detection
• Radar imaging
• Diffusion models
• Image reconstruction
• Diffusion Model
• 4D RaDAR
• Diffusion Process
• Point Cloud
• Latent Space
• High-dimensional Feature
• Radar Data
• Latent Features
• Bird’s Eye
• Accurate Point
• Process In Space
• Dense Point Cloud
• LiDAR Point
• LiDAR Point Clouds
• Improve Detection Accuracy
• Accurate Object Detection
• Point Cloud Registration
• Point Cloud Generation
• Reconstruction Module
• Raw Point Cloud
• Sparse Point Cloud
• 3D Point Cloud
• Reversible Process
• Point Cloud Data
• Pure Noise
• 3D Convolution
• Ground Points
• Voxel Grid
• Consecutive Frames