EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

MogaDepth: Multi-Order Feature Hierarchy Fusion for Lightweight Monocular Depth Estimation

Gengsheng Lin iD, Guangping Li iD

Sensors · 20.01.2026 · 26 (2) · 685

DOI: 10.3390/s26020685 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 20.01.2026. Verfasst von Gengsheng Lin und 1 weiteren Autor:innen. Beteiligte Einrichtung: School of Information Engineering, Guangdong University of Technology, Guangzhou 510000, China. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Monocular depth estimation is a fundamental task with broad applications in autonomous driving and augmented reality. While recent lightweight methods achieve impressive performance, they often neglect the interaction of mid-order semantic features, which are crucial for capturing object structures and spatial relationships that directly impact depth accuracy. To address this limitation, we propose MogaDepth, a lightweight yet expressive architecture. It introduces a novel Continuous Multi-Order Gated Aggregation (CMOGA) module that explicitly enhances mid-level feature representations through multi-order receptive fields. In addition, we present MambaSync, a global–local interaction unit that enables efficient feature communication across different contexts. Extensive experiments demonstrate that MogaDepth achieves highly competitive or superior performance on KITTI, improving key error metrics while maintaining comparable model size. On the Make3D benchmark, it consistently outperforms existing methods, showing strong robustness to domain shifts and challenging scenarios such as low-texture regions. Moreover, MogaDepth achieves an improved trade-off between accuracy and efficiency, running up to 13% faster on edge devices without compromising performance. These results establish MogaDepth as an effective and efficient solution for real-world monocular depth estimation.

Schlagwörter

Stichwörter der Autor:innen

edge deviceslightweight modelmonocular depth estimationmulti-order feature interactionsself-supervised

Autor:innen und Institutionen

  • School of Information Engineering, Guangdong University of Technology, Guangzhou 510000, China.

ORCID-Profile: Gengsheng Lin, Guangping Li

Zitieren

APA

Lin, G., & Li, G. (2026). MogaDepth: Multi-Order Feature Hierarchy Fusion for Lightweight Monocular Depth Estimation. Sensors, 26(2), 685. https://doi.org/10.3390/s26020685

Vancouver

Lin G, Li G. MogaDepth: Multi-Order Feature Hierarchy Fusion for Lightweight Monocular Depth Estimation. Sensors. 2026;26(2):685. doi:10.3390/s26020685

BibTeX
@article{Lin2026,
  author = {Lin, Gengsheng and Li, Guangping},
  title = {MogaDepth: Multi-Order Feature Hierarchy Fusion for Lightweight Monocular Depth Estimation},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {2},
  pages = {685},
  doi = {10.3390/s26020685}
}
Kostenlos starten →