EUVIMEDEUVIMED entdecken
Crossref

MHED-SLAM: Multi-Scale Hybrid Encoding-Based Decoupled SLAM

Dengfang Feng, Wenyang Qin, Zhongchen Shi, Wei Chen, Yanhui Duan, Liang Xie, Erwei Yin

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (22) · 18243-18252

DOI: 10.1609/aaai.v40i22.38887 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Dengfang Feng und 6 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Neural Radiance Fields (NeRF)-based Visual Simultaneous Localization and Mapping (SLAM) achieve superior scene geometric modeling and robust camera tracking by leveraging neural representations. Existing methods typically relied on multi-resolution hash encoding with truncated signed distance fields (TSDF) to achieve high frame rates. However, unavoidable hash collisions can lead to artifacts, and multi-view color inconsistencies in indoor scenes can result in shape-radiance ambiguity, adversely affecting geometric quality and tracking accuracy. To address these issues, we propose a novel Multi-scale Hybrid Encoding-based Decoupled SLAM (MHED-SLAM). First, to mitigate the adverse effects of hash collisions and reduce the number of learnable parameters, we innovatively fuse a coarse-scale hash tri-plane with a fine-scale hash grid within a single latent volume. Second, to enable precise geometric reconstruction and camera tracking, we decouple the reconstruction and rendering processes, independently learning a TSDF field for reconstruction and a density field for rendering. Third, we devise a Symmetric Kullback-Leibler (SKL) strategy based on ray termination distributions to align the probability distributions derived from the TSDF and density fields for their synchronous convergence. Extensive experimental evaluations demonstrate that our approach surpasses the state-of-the-art (SOTA) methods by utilizing a faster frame rate of 20 Hz and fewer parameters, while achieving higher tracking and reconstruction accuracy.

Zitieren

APA

Feng, D., Qin, W., Shi, Z., Chen, W., Duan, Y., Xie, L., & Yin, E. (2026). MHED-SLAM: Multi-Scale Hybrid Encoding-Based Decoupled SLAM. Proceedings of the AAAI Conference on Artificial Intelligence, 40(22), 18243-18252. https://doi.org/10.1609/aaai.v40i22.38887

Vancouver

Feng D, Qin W, Shi Z, Chen W, Duan Y, Xie L, et al. MHED-SLAM: Multi-Scale Hybrid Encoding-Based Decoupled SLAM. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(22):18243-18252. doi:10.1609/aaai.v40i22.38887

BibTeX
@article{Feng2026,
  author = {Feng, Dengfang and Qin, Wenyang and Shi, Zhongchen and Chen, Wei and Duan, Yanhui and Xie, Liang and Yin, Erwei},
  title = {MHED-SLAM: Multi-Scale Hybrid Encoding-Based Decoupled SLAM},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {22},
  pages = {18243--18252},
  doi = {10.1609/aaai.v40i22.38887}
}
Kostenlos starten →