4D-RaDiff: Latent Point Diffusion for 4D Radar Point Cloud Generation

arXiv:2512.14235v2 Announce Type: replace Abstract: Automotive radar has shown promising developments in environment perception due to its cost-effectiveness and robustness in adverse weather conditions. However, the limited availability of annotated radar data poses a significant challenge for advancing radar-based perception systems. To address this limitation, we propose a novel framework to generate 4D radar point clouds for training and evaluating object detectors. Unlike image-based diffusion, our method is designed to consider the sparsity and unique characteristics of radar point clouds by applying diffusion to a latent point cloud representation. Within this latent space, generation is controlled via conditioning at either the object or scene level. The proposed 4D-RaDiff converts unlabeled bounding boxes into high-quality radar annotations and transforms existing LiDAR point cloud data into realistic radar scenes. Experiments demonstrate that incorporating synthetic radar data of 4D-RaDiff as data augmentation method during training of object detection models consistently improves performance compared to training on real data only. In addition, pre-training on our synthetic radar data achieves competitive detection performance, providing a promising, scalable approach to reduce dependence on costly manual annotations.

Related

• C-DiffSET: Leveraging Latent Diffusion for SAR-to-EO Image Translation with Confidence-Guided Reliable Object Generation
• Few to Big: Prototype Expansion Network via Diffusion Learner for Point Cloud Few-shot Semantic Segmentation
• A Two-Stage Motion-Aware Framework for mmWave-based Human Mesh Recovery

Source: arXiv cs.CV | 2026-09-14