4D-RaDiff: Latent Diffusion for 4D Radar Point Cloud Generation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914203803058176 |
|---|---|
| author | Kwok, Jimmie Caesar, Holger Palffy, Andras |
| author_facet | Kwok, Jimmie Caesar, Holger Palffy, Andras |
| contents | 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 consistently improves object detection performance compared to training on real data only. In addition, pre-training on our synthetic data reduces the amount of required annotated radar data by up to 90% while achieving comparable object detection performance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_14235 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | 4D-RaDiff: Latent Diffusion for 4D Radar Point Cloud Generation Kwok, Jimmie Caesar, Holger Palffy, Andras Computer Vision and Pattern Recognition 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 consistently improves object detection performance compared to training on real data only. In addition, pre-training on our synthetic data reduces the amount of required annotated radar data by up to 90% while achieving comparable object detection performance. |
| title | 4D-RaDiff: Latent Diffusion for 4D Radar Point Cloud Generation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2512.14235 |