EUVIMEDEUVIMED entdecken
Crossref

DrivingForward: Feed-forward 3D Gaussian Splatting for Driving Scene Reconstruction from Flexible Surround-view Input

Qijian Tian, Xin Tan, Yuan Xie, Lizhuang Ma

Proceedings of the AAAI Conference on Artificial Intelligence · 11.04.2025 · 39 (7) · 7374-7382

DOI: 10.1609/aaai.v39i7.32793 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 11.04.2025. Verfasst von Qijian Tian und 3 weiteren Autor:innen. Die Arbeit wurde bisher 18-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

We propose DrivingForward, a feed-forward Gaussian Splatting model that reconstructs driving scenes from flexible surround-view input. Driving scene images from vehicle-mounted cameras are typically sparse, with limited overlap, and the movement of the vehicle further complicates the acquisition of camera extrinsics. To tackle these challenges and achieve real-time reconstruction, we jointly train a pose network, a depth network, and a Gaussian network to predict the Gaussian primitives that represent the driving scenes. The pose network and depth network determine the position of the Gaussian primitives in a self-supervised manner, without using depth ground truth and camera extrinsics during training. The Gaussian network independently predicts primitive parameters from each input image, including covariance, opacity, and spherical harmonics coefficients. At the inference stage, our model can achieve feed-forward reconstruction from flexible multi-frame surround-view input. Experiments on the nuScenes dataset show that our model outperforms existing state-of-the-art feed-forward and scene-optimized reconstruction methods in terms of reconstruction.

Zitieren

APA

Tian, Q., Tan, X., Xie, Y., & Ma, L. (2025). DrivingForward: Feed-forward 3D Gaussian Splatting for Driving Scene Reconstruction from Flexible Surround-view Input. Proceedings of the AAAI Conference on Artificial Intelligence, 39(7), 7374-7382. https://doi.org/10.1609/aaai.v39i7.32793

Vancouver

Tian Q, Tan X, Xie Y, Ma L. DrivingForward: Feed-forward 3D Gaussian Splatting for Driving Scene Reconstruction from Flexible Surround-view Input. Proceedings of the AAAI Conference on Artificial Intelligence. 2025;39(7):7374-7382. doi:10.1609/aaai.v39i7.32793

BibTeX
@article{Tian2025,
  author = {Tian, Qijian and Tan, Xin and Xie, Yuan and Ma, Lizhuang},
  title = {DrivingForward: Feed-forward 3D Gaussian Splatting for Driving Scene Reconstruction from Flexible Surround-view Input},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2025},
  volume = {39},
  number = {7},
  pages = {7374--7382},
  doi = {10.1609/aaai.v39i7.32793}
}
Kostenlos starten →