English

Generative Adversarial Synthesis of Radar Point Cloud Scenes

Computer Vision and Pattern Recognition 2024-10-18 v1 Machine Learning Image and Video Processing

Abstract

For the validation and verification of automotive radars, datasets of realistic traffic scenarios are required, which, how ever, are laborious to acquire. In this paper, we introduce radar scene synthesis using GANs as an alternative to the real dataset acquisition and simulation-based approaches. We train a PointNet++ based GAN model to generate realistic radar point cloud scenes and use a binary classifier to evaluate the performance of scenes generated using this model against a test set of real scenes. We demonstrate that our GAN model achieves similar performance (~87%) to the real scenes test set.

Keywords

Cite

@article{arxiv.2410.13526,
  title  = {Generative Adversarial Synthesis of Radar Point Cloud Scenes},
  author = {Muhammad Saad Nawaz and Thomas Dallmann and Torsten Schoen and Dirk Heberling},
  journal= {arXiv preprint arXiv:2410.13526},
  year   = {2024}
}

Comments

ICMIM 2024; 7th IEEE MTT Conference

R2 v1 2026-06-28T19:25:49.824Z