Improved Classification-Based Monocular Depth Estimation for Robust Generalization of Diverse Scenes
Applied Sciences · 11.08.2026 · 16 (16) · 8003
DOI: 10.3390/app16168003 ↗Kurz gefasst
Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 11.08.2026. Verfasst von Wei-Jong Yang und 2 weiteren Autor:innen. Die Arbeit nennt 52 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Science and Technology Council, Taiwan.
Abstract (Originalsprache)
Recently, monocular depth estimation methods with neural networks trained using an image-depth database have become widely used and prevalent techniques. However, their generalization abilities are often constrained by training data: models trained on indoor datasets may perform well on other indoor datasets but exhibit some performance degradation for outdoor scenes. Therefore, developing a monocular depth estimation network with strong generalization capability for diverse scenes is challenging. In this paper, we propose a monocular depth estimation model that exhibits high generalizability and performs effectively across various scenarios without additional fine-tuning. In terms of model design, we adopt a powerful visual encoder to extract rich semantic features and incorporate the proposed multiple depth prediction heads with self-adaptability for robust depth estimation. With the designed modules and architectural refinements, the proposed model achieves a favorable balance between parameter efficiency and inference accuracy. After testing several unseen datasets, the simulation results demonstrate that the proposed method achieves better estimation performance than the baseline method and shows better robust visualization performance on multiple seen and unseen datasets.
Förderung
- National Science and Technology Council, Taiwan
Zitieren
APA
Yang, W., Wu, G., & Yang, J. (2026). Improved Classification-Based Monocular Depth Estimation for Robust Generalization of Diverse Scenes. Applied Sciences, 16(16), 8003. https://doi.org/10.3390/app16168003
Vancouver
Yang W, Wu G, Yang J. Improved Classification-Based Monocular Depth Estimation for Robust Generalization of Diverse Scenes. Applied Sciences. 2026;16(16):8003. doi:10.3390/app16168003
BibTeX
@article{Yang2026,
author = {Yang, Wei-Jong and Wu, Guo-Wei and Yang, Jar-Ferr},
title = {Improved Classification-Based Monocular Depth Estimation for Robust Generalization of Diverse Scenes},
journal = {Applied Sciences},
year = {2026},
volume = {16},
number = {16},
pages = {8003},
doi = {10.3390/app16168003}
}
EUVIMED