Revisiting CNNs for Monocular Depth Estimation: A Synthetic-to-Real Perspective
Journal of the Brazilian Computer Society · 05.10.2026 · 32 (1) · 2350-2364
DOI: 10.5753/jbcs.2026.5874 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of the Brazilian Computer Society, online erschienen am 05.10.2026. Verfasst von Luís Gustavo Lorgus Decker und 4 weiteren Autor:innen. Die Arbeit nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Monocular depth estimation is crucial for autonomous systems, augmented reality, and scene understanding. While Vision Transformers (ViTs) excel at capturing global context, their need for large amounts of data makes them impractical for smaller datasets, leaving convolutional neural networks (CNNs) as a viable alternative. This study evaluates CNN-based architectures for monocular depth estimation, proposing a fully convolutional model optimized for efficiency and generalization. Trained solely on synthetic datasets with precise depth annotations, our model avoids real-world data limitations. We assess its performance on synthetic validation sets and real-world datasets without fine-tuning, examining its capacity for domain generalization. Results show that CNNs, with optimized architectures and training, achieve strong depth estimation and enable synthetic-to-real transfer, with an AbsREL of 0.077 on KITTI and 0.099 on NYU Depth. These findings challenge the assumption that real-world data is essential for generalization.
Zitieren
APA
Decker, L. G. L., Campana, J. L. F., Souza, M. R. E., Maia, H. D. A., & Pedrini, H. (2026). Revisiting CNNs for Monocular Depth Estimation: A Synthetic-to-Real Perspective. Journal of the Brazilian Computer Society, 32(1), 2350-2364. https://doi.org/10.5753/jbcs.2026.5874
Vancouver
Decker LGL, Campana JLF, Souza MRE, Maia HDA, Pedrini H. Revisiting CNNs for Monocular Depth Estimation: A Synthetic-to-Real Perspective. Journal of the Brazilian Computer Society. 2026;32(1):2350-2364. doi:10.5753/jbcs.2026.5874
BibTeX
@article{Decker2026,
author = {Decker, Luís Gustavo Lorgus and Campana, Jose Luis Flores and Souza, Marcos Roberto e and Maia, Helena de Almeida and Pedrini, Helio},
title = {Revisiting CNNs for Monocular Depth Estimation: A Synthetic-to-Real Perspective},
journal = {Journal of the Brazilian Computer Society},
year = {2026},
volume = {32},
number = {1},
pages = {2350--2364},
doi = {10.5753/jbcs.2026.5874}
}
EUVIMED