EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Learning Depth from Focus with Multi-Candidate Estimation and Proximal Refinement

Muhammad Tariq Mahmood

Electronics · 09.06.2026 · 15 (12) · 2548

DOI: 10.3390/electronics15122548 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Electronics, online erschienen am 09.06.2026. Verfasst von Muhammad Tariq Mahmood. Die Arbeit nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Research Promotion Program Koreatech.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In this paper, we propose a novel Depth from Focus (DFF) framework that formulates depth estimation as an energy minimization problem and unrolls the corresponding iterative optimization into a trainable neural architecture. Given a focal stack, a deep feature extractor constructs a learned focus volume that encodes defocus and structural cues. Based on this representation, multiple candidate depth maps are generated using a plane-based probabilistic formulation, while an attention mechanism adaptively assigns pixel-wise confidence weights to each candidate. The depth estimation is performed through an iterative refinement process, where each stage corresponds to a learned proximal update implemented via lightweight conditional networks. These updates incorporate focus consistency, adaptive step sizes, and learned regularization priors, enabling effective integration of physical imaging constraints with data-driven modeling. A final refinement module further enhances prediction accuracy by fusing the refined depth, focus volume features, and candidate hypotheses to estimate residual corrections. The entire framework is trained end-to-end, ensuring coherent optimization across all components. Experimental results demonstrate that the proposed method achieves improved robustness and accuracy, particularly in low-texture and noisy regions, while preserving interpretability through its unfolding-based design.

Förderung

  • Research Promotion Program Koreatech

Zitieren

APA

Mahmood, M. T. (2026). Learning Depth from Focus with Multi-Candidate Estimation and Proximal Refinement. Electronics, 15(12), 2548. https://doi.org/10.3390/electronics15122548

Vancouver

Mahmood MT. Learning Depth from Focus with Multi-Candidate Estimation and Proximal Refinement. Electronics. 2026;15(12):2548. doi:10.3390/electronics15122548

BibTeX
@article{Mahmood2026,
  author = {Mahmood, Muhammad Tariq},
  title = {Learning Depth from Focus with Multi-Candidate Estimation and Proximal Refinement},
  journal = {Electronics},
  year = {2026},
  volume = {15},
  number = {12},
  pages = {2548},
  doi = {10.3390/electronics15122548}
}
Kostenlos starten →