EUVIMEDEUVIMED entdecken
Crossref

NeRF-LiDAR: Generating Realistic LiDAR Point Clouds with Neural Radiance Fields

Junge Zhang, Feihu Zhang, Shaochen Kuang, Li Zhang

Proceedings of the AAAI Conference on Artificial Intelligence · 24.03.2024 · 38 (7) · 7178-7186

DOI: 10.1609/aaai.v38i7.28546 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 24.03.2024. Verfasst von Junge Zhang und 3 weiteren Autor:innen. Die Arbeit wurde bisher 54-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Labelling LiDAR point clouds for training autonomous driving is extremely expensive and difficult. LiDAR simulation aims at generating realistic LiDAR data with labels for training and verifying self-driving algorithms more efficiently. Recently, Neural Radiance Fields (NeRF) have been proposed for novel view synthesis using implicit reconstruction of 3D scenes. Inspired by this, we present NeRF-LIDAR, a novel LiDAR simulation method that leverages real-world information to generate realistic LIDAR point clouds. Different from existing LiDAR simulators, we use real images and point cloud data collected by self-driving cars to learn the 3D scene representation, point cloud generation and label rendering. We verify the effectiveness of our NeRF-LiDAR by training different 3D segmentation models on the generated LiDAR point clouds. It reveals that the trained models are able to achieve similar accuracy when compared with the same model trained on the real LiDAR data. Besides, the generated data is capable of boosting the accuracy through pre-training which helps reduce the requirements of the real labeled data. Code is available at https://github.com/fudan-zvg/NeRF-LiDAR

Zitieren

APA

Zhang, J., Zhang, F., Kuang, S., & Zhang, L. (2024). NeRF-LiDAR: Generating Realistic LiDAR Point Clouds with Neural Radiance Fields. Proceedings of the AAAI Conference on Artificial Intelligence, 38(7), 7178-7186. https://doi.org/10.1609/aaai.v38i7.28546

Vancouver

Zhang J, Zhang F, Kuang S, Zhang L. NeRF-LiDAR: Generating Realistic LiDAR Point Clouds with Neural Radiance Fields. Proceedings of the AAAI Conference on Artificial Intelligence. 2024;38(7):7178-7186. doi:10.1609/aaai.v38i7.28546

BibTeX
@article{Zhang2024,
  author = {Zhang, Junge and Zhang, Feihu and Kuang, Shaochen and Zhang, Li},
  title = {NeRF-LiDAR: Generating Realistic LiDAR Point Clouds with Neural Radiance Fields},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2024},
  volume = {38},
  number = {7},
  pages = {7178--7186},
  doi = {10.1609/aaai.v38i7.28546}
}
Kostenlos starten →