EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

RDANet: Parameter-Efficient Cross-Dataset Adaptation for Event-Based Monocular Depth Estimation

Md Abdur Rahaman, Yong Ju Jung

Applied Sciences · 03.05.2026 · 16 (9) · 4501

DOI: 10.3390/app16094501 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 03.05.2026. Verfasst von Md Abdur Rahaman und 1 weiteren Autor:innen. Die Arbeit nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Research Foundation of Korea, Gachon University.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Event cameras capture sparse, high-temporal-resolution visual information, making them attractive for challenging scenarios with fast motion and severe illumination changes. However, event-based depth models trained on one real-world benchmark often degrade substantially when transferred to another, revealing a practical cross-dataset domain shift between real sensor datasets. In this work, we study parameter-efficient adaptation from MVSEC to DSEC using a frozen VFM-based recurrent depth backbone. We systematically compare several parameter-efficient fine-tuning (PEFT) strategies, including Bias-only, Adapter, Decoder Weight Tuning, ConvLSTM-only, and FiLM-based modulation, under labeled few-shot adaptation. Across three random seeds, Bias-only achieves the best few-shot accuracy, reaching 0.189 AbsRel with 150 calibration samples. Decoder-side FiLM provides the best accuracy–efficiency trade-off, maintaining stable performance while updating only 2048 parameters, and reaches 0.176 AbsRel when trained with the full DSEC training set under our protocol. Our study shows that tuning native pretrained parameters is a strong baseline in this specific MVSEC → DSEC event-depth adaptation setting, whereas higher-capacity auxiliary modules are less effective under limited target-domain supervision. These results establish a controlled MVSEC → DSEC benchmark and provide practical guidance for adapting event-based monocular depth models under cross-dataset transfer.

Förderung

  • National Research Foundation of Korea
  • Gachon University

Zitieren

APA

Rahaman, M. A., & Jung, Y. J. (2026). RDANet: Parameter-Efficient Cross-Dataset Adaptation for Event-Based Monocular Depth Estimation. Applied Sciences, 16(9), 4501. https://doi.org/10.3390/app16094501

Vancouver

Rahaman MA, Jung YJ. RDANet: Parameter-Efficient Cross-Dataset Adaptation for Event-Based Monocular Depth Estimation. Applied Sciences. 2026;16(9):4501. doi:10.3390/app16094501

BibTeX
@article{Rahaman2026,
  author = {Rahaman, Md Abdur and Jung, Yong Ju},
  title = {RDANet: Parameter-Efficient Cross-Dataset Adaptation for Event-Based Monocular Depth Estimation},
  journal = {Applied Sciences},
  year = {2026},
  volume = {16},
  number = {9},
  pages = {4501},
  doi = {10.3390/app16094501}
}
Kostenlos starten →