EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Improving Domain Generalization via Bridging Convolutional Neural Networks and State-Space Models in Monocular Depth Estimation

Cătălin-Cristian Botean, Călin-Adrian Popa

Applied Sciences · 17.05.2026 · 16 (10) · 4999

DOI: 10.3390/app16104999 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 17.05.2026. Verfasst von Cătălin-Cristian Botean und 1 weiteren Autor:innen. Die Arbeit nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Self-supervised monocular depth estimation (MDE) has emerged as a cost-effective alternative to traditional depth sensing approaches, which often require expensive equipment or complex configurations. However, these models often fail to maintain high performance on unseen domains, presenting a considerable issue for real-world applications, such as autonomous driving, where the ability to adapt consistently across various conditions is essential for ensuring safety. In this paper, we propose a novel lightweight network designed to separate domain-specific style and domain-invariant content within feature representation statistics, removing the style information that contributes to the domain shift. Furthermore, to address the convolutional neural network’s limited local scope, we inject state-space model blocks inside our encoder architecture in order to capture extensive contextual information, yet having a minimum number of trainable parameters. Experiments on popular outdoor depth estimation benchmarks, KITTI and Make3D, demonstrate superior performance to other recent networks with similar size.

Zitieren

APA

Botean, C., & Popa, C. (2026). Improving Domain Generalization via Bridging Convolutional Neural Networks and State-Space Models in Monocular Depth Estimation. Applied Sciences, 16(10), 4999. https://doi.org/10.3390/app16104999

Vancouver

Botean C, Popa C. Improving Domain Generalization via Bridging Convolutional Neural Networks and State-Space Models in Monocular Depth Estimation. Applied Sciences. 2026;16(10):4999. doi:10.3390/app16104999

BibTeX
@article{Botean2026,
  author = {Botean, Cătălin-Cristian and Popa, Călin-Adrian},
  title = {Improving Domain Generalization via Bridging Convolutional Neural Networks and State-Space Models in Monocular Depth Estimation},
  journal = {Applied Sciences},
  year = {2026},
  volume = {16},
  number = {10},
  pages = {4999},
  doi = {10.3390/app16104999}
}
Kostenlos starten →