EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Robust Shape-from-Focus via Physics-Inspired Distortion-Aware Focal Depth Regression

Xin Li, Wei Shen, Jian Li iD, Zhongsheng Zhai, Xuhong Guan, Zili Lei

Sensors · 27.05.2026 · 26 (11) · 3390

DOI: 10.3390/s26113390 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 27.05.2026. Verfasst von Xin Li und 5 weiteren Autor:innen. Beteiligte Einrichtung: Hubei Key Laboratory of Modern Manufacturing Quantity Engineering, School of Mechanical Engineering, Hubei University of Technology, Wuhan 430068, Ch…. Die Arbeit nennt 51 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Hubei University of Technology, National Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Shape-from-Focus (SFF) is attractive for microscopic three-dimensional measurement, but high dynamic range (HDR) surfaces and weak-textured surfaces distort the focus curve through saturation, spurious peaks, and low signal-to-noise ratios. These distortions violate the unimodal assumption used by Gaussian peak localization and limit post-processing-only correction. This paper proposes a physics-guided distortion-aware SFF pipeline for opaque single-surface targets. The Distortion-Aware Focal Depth Regression Network (DAFDR-Net) learns from synthetic focus-curve distortions and uses Channel-wise Feature Attention (CFA) and Soft Peak Localization to reweight distortion-sensitive temporal-response features while preserving a peak-localization prior. Its foreground validity output is further used for confidence-guided adaptive smoothing. On an HDR free-form surface dataset, the proposed pipeline reduces RMSE by 36.5% relative to an MRF optimization method and compresses the 99th-percentile absolute error from 0.181 to 0.033. On weak-textured monocrystalline silicon wafer data, it reduces flat-region depth standard deviation by 51.3%.

Schlagwörter

Stichwörter der Autor:innen

Shape-from-Focuschannel-wise feature attentionconfidence-guided smoothinghigh dynamic rangephysics-guided depth regressionweak-textured surfaces

Autor:innen und Institutionen

  • Hubei Key Laboratory of Modern Manufacturing Quantity Engineering, School of Mechanical Engineering, Hubei University of Technology, Wuhan 430068, China.
  • School of Mechanical and Electrical Engineering, Changsha University, Changsha 410022, China.

ORCID-Profile: Jian Li

Förderung

  • Hubei University of Technology
  • National Natural Science Foundation of China

Zitieren

APA

Li, X., Shen, W., Li, J., Zhai, Z., Guan, X., & Lei, Z. (2026). Robust Shape-from-Focus via Physics-Inspired Distortion-Aware Focal Depth Regression. Sensors, 26(11), 3390. https://doi.org/10.3390/s26113390

Vancouver

Li X, Shen W, Li J, Zhai Z, Guan X, Lei Z. Robust Shape-from-Focus via Physics-Inspired Distortion-Aware Focal Depth Regression. Sensors. 2026;26(11):3390. doi:10.3390/s26113390

BibTeX
@article{Li2026,
  author = {Li, Xin and Shen, Wei and Li, Jian and Zhai, Zhongsheng and Guan, Xuhong and Lei, Zili},
  title = {Robust Shape-from-Focus via Physics-Inspired Distortion-Aware Focal Depth Regression},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {11},
  pages = {3390},
  doi = {10.3390/s26113390}
}
Kostenlos starten →