EUVIMEDEUVIMED entdecken
Crossref

Seeing in Double: Dual-Granularity BEV Segmentation via Mamba-Driven Alignment and Polar-Decoupled Experts

Jiaxin Cai, Rui Lin, Jingze Su, Qi Li, Wenjie Yang, Yuanlong Yu, Wenxi Liu

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (4) · 2516-2524

DOI: 10.1609/aaai.v40i4.37238 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Jiaxin Cai und 6 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Bird's Eye View (BEV) representation has become pivotal for autonomous driving, yet existing polar coordinate-based approaches face two critical limitations: (1) distant semantic misprojection caused by radial resolution decay, and (2) region-specific geometric distortions from non-uniform polar discretization. To address these issues, we propose a novel framework addressing these challenges through three key innovations. First, we present a bilateral heterogeneous network constructs multi-granularity BEV spaces, efficiently exploiting dual-resolution visual information for distant detail preservation. Second, we employ an align-fusion strategy for multi-granularity feature aggregation. Specifically, the Mamba-Based Cross-Resolution Alignment module establishes semantic consistency for perspective features through shared state-space optimization. In the later stage, the Adaptive BEV Space Selector dynamically aggregates multi-granularity BEV features. Third, we introduce a Mixture of Radial-Angular Decoupled Experts, which employs polar-aware expert routing to disentangle radial compression and angular shear distortions through specialized geometric refinement. Comprehensive experiments on nuScenes and Lyft L5 demonstrate the state-of-the-art performance of our model across various resolution settings, visibility filtering, and perception ranges.

Zitieren

APA

Cai, J., Lin, R., Su, J., Li, Q., Yang, W., Yu, Y., & Liu, W. (2026). Seeing in Double: Dual-Granularity BEV Segmentation via Mamba-Driven Alignment and Polar-Decoupled Experts. Proceedings of the AAAI Conference on Artificial Intelligence, 40(4), 2516-2524. https://doi.org/10.1609/aaai.v40i4.37238

Vancouver

Cai J, Lin R, Su J, Li Q, Yang W, Yu Y, et al. Seeing in Double: Dual-Granularity BEV Segmentation via Mamba-Driven Alignment and Polar-Decoupled Experts. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(4):2516-2524. doi:10.1609/aaai.v40i4.37238

BibTeX
@article{Cai2026,
  author = {Cai, Jiaxin and Lin, Rui and Su, Jingze and Li, Qi and Yang, Wenjie and Yu, Yuanlong and Liu, Wenxi},
  title = {Seeing in Double: Dual-Granularity BEV Segmentation via Mamba-Driven Alignment and Polar-Decoupled Experts},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {4},
  pages = {2516--2524},
  doi = {10.1609/aaai.v40i4.37238}
}
Kostenlos starten →