A Hybrid UNet with Attention and a Perceptual Loss Function for Monocular Depth Estimation

Hamidullah Turkmen and Devrim Akgun ()
Additional contact information
Hamidullah Turkmen: Computer and Informatics Engineering Department, Institute of Natural Science and Technology, Sakarya University, Esentepe Campus, 54050 Serdivan, Sakarya, Türkiye
Devrim Akgun: Software Engineering Department, Faculty of Computer and Information Sciences, Sakarya University, 54050 Serdivan, Sakarya, Türkiye

Mathematics, 2025, vol. 13, issue 16, 1-19

Abstract: Monocular depth estimation is a crucial technique in computer vision that determines the depth or distance of objects in a scene using a single 2D image captured by a camera. UNet-based models are a fundamental architecture for monocular depth estimation, due to their effective encoder–decoder structure. This study presents an effective depth estimation model based on a hybrid UNet architecture that incorporates ensemble features. The new model integrates Transformer-based attention blocks to capture global context and an encoder built on ResNet18 to extract spatial features. Additionally, a novel Boundary-Aware Depth Consistency Loss (BADCL) function has been introduced to enhance accuracy. This function features dynamic scaling, smoothness regularization, and boundary-aware weighting, which provides sharper edges, smoother depth transitions, and scale-consistent predictions. The proposed model has been evaluated on the NYU Depth V2 dataset, achieving a Structural Similarity Index Measure (SSIM) of 99.8%. The performance of the proposed model indicates increased depth accuracy compared to state-of-the-art methods.

Keywords: monocular depth estimation; autonomous driving; transformer attention; hybrid UNet model; boundary-aware depth consistency loss (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2227-7390/13/16/2567/pdf (application/pdf)
https://www.mdpi.com/2227-7390/13/16/2567/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jmathe:v:13:y:2025:i:16:p:2567-:d:1721885

Access Statistics for this article

Mathematics is currently edited by Ms. Emma He

More articles in Mathematics from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().