EUVIMEDEUVIMED entdecken
Crossref

S-NeRF++: Autonomous Driving Simulation via Neural Reconstruction and Generation

Yurui Chen, Junge Zhang, Ziyang Xie, Wenye Li, Feihu Zhang, Jiachen Lu, Li Zhang

IEEE Transactions on Pattern Analysis and Machine Intelligence · 2025-06 · 47 (6) · 4358-4376

DOI: 10.1109/tpami.2025.3543072 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025-06. Verfasst von Yurui Chen und 6 weiteren Autor:innen. Die Arbeit wurde bisher 31-mal zitiert (Crossref) und nennt 86 Literaturangaben. Gefördert von: National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Autonomous driving simulation system plays a crucial role in enhancing self-driving data and simulating complex and rare traffic scenarios, ensuring navigation safety. However, traditional simulation systems, which often heavily rely on manual modeling and 2D image editing, struggled with scaling to extensive scenes and generating realistic simulation data. In this study, we present S-NeRF++, an innovative autonomous driving simulation system based on neural reconstruction. Trained on widely-used self-driving datasets, such as nuScenes and Waymo, S-NeRF++ can generate a large number of realistic street scenes and foreground objects with high rendering quality as well as offering considerable flexibility in manipulation and simulation. Specifically, S-NeRF++ is an enhanced neural radiance field for synthesizing large-scale scenes and moving vehicles, with improved scene parameterization and camera pose learning. The system effectively utilizes noisy and sparse LiDAR data to refine training and address depth outliers, ensuring high-quality reconstruction and novel-view rendering. It also provides a diverse foreground asset bank by reconstructing and generating different foreground vehicles to support comprehensive scenario creation. Moreover, we have developed an advanced foreground-background fusion pipeline that skillfully integrates illumination and shadow effects, further enhancing the realism of our simulations. With the high-quality simulated data provided by our S-NeRF++, we found the perception methods enjoy performance boosts on several autonomous driving downstream tasks, further demonstrating our proposed simulator's effectiveness.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Chen, Y., Zhang, J., Xie, Z., Li, W., Zhang, F., Lu, J., & Zhang, L. (2025). S-NeRF++: Autonomous Driving Simulation via Neural Reconstruction and Generation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 47(6), 4358-4376. https://doi.org/10.1109/tpami.2025.3543072

Vancouver

Chen Y, Zhang J, Xie Z, Li W, Zhang F, Lu J, et al. S-NeRF++: Autonomous Driving Simulation via Neural Reconstruction and Generation. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2025;47(6):4358-4376. doi:10.1109/tpami.2025.3543072

BibTeX
@article{Chen2025,
  author = {Chen, Yurui and Zhang, Junge and Xie, Ziyang and Li, Wenye and Zhang, Feihu and Lu, Jiachen and Zhang, Li},
  title = {S-NeRF++: Autonomous Driving Simulation via Neural Reconstruction and Generation},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2025},
  volume = {47},
  number = {6},
  pages = {4358--4376},
  doi = {10.1109/tpami.2025.3543072}
}
Kostenlos starten →