GAN-Based LiDAR Intensity Simulation
Marcus R, Gabel F, Knoop N, Stamminger M (2023)
Publication Type: Conference contribution, Original article
Publication year: 2023
Journal
Publisher: Springer Science and Business Media Deutschland GmbH
Book Volume: 1875 CCIS
Pages Range: 419-433
Conference Proceedings Title: Communications in Computer and Information Science
Event location: Rome, ITA
ISBN: 9783031390586
DOI: 10.1007/978-3-031-39059-3_28
Abstract
Realistic vehicle sensor simulation is an important element in developing autonomous driving. As physics-based implementations of visual sensors like LiDAR are complex in practice, data-based approaches promise solutions. Using pairs of camera images and LiDAR scans from real test drives, GANs can be trained to translate between them. For this process, we contribute two additions. First, we exploit the camera images, acquiring segmentation data and dense depth maps as additional input for training. Second, we test the performance of the LiDAR simulation by testing how well an object detection network generalizes between real and synthetic point clouds to enable evaluation without ground truth point clouds. Combining both, we simulate LiDAR point clouds and demonstrate their realism.
Authors with CRIS profile
Involved external institutions
Germany (DE)How to cite
APA:
Marcus, R., Gabel, F., Knoop, N., & Stamminger, M. (2023). GAN-Based LiDAR Intensity Simulation. In Donatello Conte, Ana Fred, Oleg Gusikhin, Carlo Sansone (Eds.), Communications in Computer and Information Science (pp. 419-433). Rome, ITA: Springer Science and Business Media Deutschland GmbH.
MLA:
Marcus, Richard, et al. "GAN-Based LiDAR Intensity Simulation." Proceedings of the Proceedings of the 4th International Conference on Deep Learning Theory and Applications, DeLTA 2023, Rome, ITA Ed. Donatello Conte, Ana Fred, Oleg Gusikhin, Carlo Sansone, Springer Science and Business Media Deutschland GmbH, 2023. 419-433.
BibTeX: Download