We present RadarGen, a diffusion model for synthesizing realistic automotive radar point clouds from multi-view camera imagery. RadarGen adapts efficient image-latent diffusion to the radar domain by representing radar measurements in bird's-eye-view form that encodes spatial structure together with radar cross section (RCS) and Doppler attributes. A lightweight recovery step reconstructs point clouds from the generated maps. To better align generation with the visual scene, RadarGen incorporates BEV-aligned depth, semantic, and motion cues extracted from pretrained foundation models, which guide the stochastic generation process toward physically plausible radar patterns. Conditioning on images makes the approach broadly compatible, in principle, with existing visual datasets and simulation frameworks, offering a scalable direction for multimodal generative simulation. Evaluations on large-scale driving data show that RadarGen captures characteristic radar measurement distributions and reduces the gap to perception models trained on real data, marking a step toward unified generative simulation across sensing modalities.
This repository contains the pre-trained weights for RadarGen, trained on the
MAN TruckScenes dataset.
1from radargen.inference import RadarGenInference
2from radargen.datasets import get_adapter
3
4# Load dataset adapter
5adapter = get_adapter("truckscenes", trucksc=trucksc_obj)
6
7# Initialize model
8model = RadarGenInference(
9 adapter=adapter,
10 config_path="configs/RadarGen_600M_512px_TS_inference.yaml",
11 checkpoint_path="hf://TomerBo/RadarGen_600M_512px_TS/RadarGen_600M_512px_TS.safetensors"
12)
13
14# Generate point cloud from two consecutive frames
15pcl = model.from_sample_data(sample_t0, sample_t1)
This model inherits its license from
SANA weights (NSCL v2-custom) and the
MAN TruckScenes dataset (CC BY-NC-SA 4.0). Non-commercial use only.
If you find our work useful, please consider starring ⭐ the repository and citing our paper:
1@article{borreda2025radargen,
2 title={RadarGen: Automotive Radar Point Cloud Generation from Cameras},
3 author={Borreda, Tomer and Ding, Fangqiang and Fidler, Sanja and Huang, Shengyu and Litany, Or},
4 journal={arXiv preprint arXiv:2512.17897},
5 year={2025}
6}
