EUVIMEDEUVIMED entdecken
Crossref

Street Gaussians: Modeling Dynamic Urban Scenes With Gaussian Primitives

Sida Peng, Yushi Long, Yunzhi Yan, Haotong Lin, Chenxu Zhou, Haiyang Sun, Kun Zhan, Xianpeng Lang, Hujun Bao, Xiaowei Zhou

IEEE Transactions on Pattern Analysis and Machine Intelligence · 2026-03 · 48 (3) · 3355-3367

DOI: 10.1109/tpami.2025.3634385 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2026-03. Verfasst von Sida Peng und 9 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 80 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Li Auto, Zhejiang University Education Foundation Qizhen Scholar Foundation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This paper aims to tackle the problem of modeling dynamic urban streets for autonomous driving scenes. Recent methods extend NeRF by incorporating tracked vehicle poses to animate vehicles, enabling photo-realistic view synthesis of dynamic urban street scenes. However, significant limitations are their slow training and rendering speed. We introduce Street Gaussians, a new explicit scene representation that tackles these limitations. Specifically, the dynamic urban scene is represented as a set of point clouds equipped with semantic logits and Gaussian primitives, each associated with either a foreground object or the background. To model the dynamics of foreground objects, each object point cloud is optimized with optimizable tracked poses, along with a 4D spherical harmonics model for the dynamic appearance. The explicit representation allows easy composition of objects and background, which in turn allows for scene editing operations and rendering at 135 FPS (1066 * 1600 resolution) within half an hour of training. The proposed method is evaluated on multiple challenging benchmarks, including KITTI and Waymo Open datasets. Experiments show that the proposed method consistently outperforms state-of-the-art methods across all datasets.

Förderung

  • National Natural Science Foundation of China
  • Li Auto
  • Zhejiang University Education Foundation Qizhen Scholar Foundation
  • Information Technology Center and State Key Lab of CAD&CG
  • Zhejiang University

Zitieren

APA

Peng, S., Long, Y., Yan, Y., Lin, H., Zhou, C., Sun, H., Zhan, K., Lang, X., Bao, H., & Zhou, X. (2026). Street Gaussians: Modeling Dynamic Urban Scenes With Gaussian Primitives. IEEE Transactions on Pattern Analysis and Machine Intelligence, 48(3), 3355-3367. https://doi.org/10.1109/tpami.2025.3634385

Vancouver

Peng S, Long Y, Yan Y, Lin H, Zhou C, Sun H, et al. Street Gaussians: Modeling Dynamic Urban Scenes With Gaussian Primitives. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2026;48(3):3355-3367. doi:10.1109/tpami.2025.3634385

BibTeX
@article{Peng2026,
  author = {Peng, Sida and Long, Yushi and Yan, Yunzhi and Lin, Haotong and Zhou, Chenxu and Sun, Haiyang and Zhan, Kun and Lang, Xianpeng and Bao, Hujun and Zhou, Xiaowei},
  title = {Street Gaussians: Modeling Dynamic Urban Scenes With Gaussian Primitives},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2026},
  volume = {48},
  number = {3},
  pages = {3355--3367},
  doi = {10.1109/tpami.2025.3634385}
}
Kostenlos starten →