EUVIMEDEUVIMED entdecken
Crossref

RGBDS-SLAM: A RGB-D Semantic Dense SLAM Based on 3D Multi Level Pyramid Gaussian Splatting

Zhenzhong Cao, Chenyang Zhao, Qianyi Zhang, Jinzheng Guang, Yinuo Song, Jingtai Liu

IEEE Robotics and Automation Letters · 2025-05 · 10 (5) · 4778-4785

DOI: 10.1109/lra.2025.3553049 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Robotics and Automation Letters, 2025-05. Verfasst von Zhenzhong Cao und 5 weiteren Autor:innen. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 35 Literaturangaben. Gefördert von: National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

High-fidelity reconstruction is crucial for dense SLAM. Recent popular methods utilize 3D Gaussian splatting (3D GS) techniques for RGB, depth, and semantic reconstruction of scenes. However, these methods ignore issues of detail and consistency in different parts of the scene. To address this, we propose RGBDS-SLAM, a RGB-D semantic dense SLAM system based on 3D multi-level pyramid Gaussian splatting, which enables high-fidelity dense reconstruction of scene RGB, depth, and semantics. In this system, we introduce a 3D multi-level pyramid Gaussian splatting method that restores scene details by extracting multi-level image pyramids for Gaussian splatting training, ensuring consistency in RGB, depth, and semantic reconstructions. Additionally, we design a tightly-coupled multi-features reconstruction optimization mechanism, allowing the reconstruction accuracy of RGB, depth, and semantic features to mutually enhance each other during the rendering optimization process. Extensive quantitative, qualitative, and ablation experiments on the Replica and ScanNet public datasets demonstrate that our proposed method outperforms current state-of-the-art methods, which achieves great improvement by 11.13% in PSNR and 68.57% in LPIPS.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Cao, Z., Zhao, C., Zhang, Q., Guang, J., Song, Y., & Liu, J. (2025). RGBDS-SLAM: A RGB-D Semantic Dense SLAM Based on 3D Multi Level Pyramid Gaussian Splatting. IEEE Robotics and Automation Letters, 10(5), 4778-4785. https://doi.org/10.1109/lra.2025.3553049

Vancouver

Cao Z, Zhao C, Zhang Q, Guang J, Song Y, Liu J. RGBDS-SLAM: A RGB-D Semantic Dense SLAM Based on 3D Multi Level Pyramid Gaussian Splatting. IEEE Robotics and Automation Letters. 2025;10(5):4778-4785. doi:10.1109/lra.2025.3553049

BibTeX
@article{Cao2025,
  author = {Cao, Zhenzhong and Zhao, Chenyang and Zhang, Qianyi and Guang, Jinzheng and Song, Yinuo and Liu, Jingtai},
  title = {RGBDS-SLAM: A RGB-D Semantic Dense SLAM Based on 3D Multi Level Pyramid Gaussian Splatting},
  journal = {IEEE Robotics and Automation Letters},
  year = {2025},
  volume = {10},
  number = {5},
  pages = {4778--4785},
  doi = {10.1109/lra.2025.3553049}
}
Kostenlos starten →