EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Feature-Level Reliability of Directional-Kernel Richardson–Lucy Deblurring Under Kernel-Length and Direction Controls

Xiangchen Ku, Runqing Xue iD, Yichen Liang

Sensors · 19.08.2026 · 26 (16) · 5249

DOI: 10.3390/s26165249 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 19.08.2026. Verfasst von Xiangchen Ku und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Mechanical and Electronic Engineering, School of Mechatronics Engineering, Henan University of Science and Technology, Luoyang 471003, …. Die Arbeit nennt 54 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Henan University of Science and Technology, the Major Science and Technology Projects of Henan Province.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Image restoration lies between camera acquisition and geometric estimation, but pixel improvements may not transfer to motion estimates. We evaluated directional-kernel Richardson–Lucy (RL) deblurring under kernel-length and direction controls. The restoration analysis covered 3071 paired GoPro, RealBlur-J, and RealBlur-R images. An exploratory feature analysis used a fixed 155-image subset with Oriented FAST and Rotated BRIEF (ORB), scale-invariant feature transform (SIFT), two geometry models, ten random directions, NAFNet, and Restormer. A separate task analysis used ten red–green–blue plus depth (RGB-D) sequences from the Technical University of Munich (TUM) benchmark, synthetic 20 ms exposures, and fixed RGB-D perspective-n-point odometry. Estimated directions contained information relative to random angles, yet the tested global RL branches remained below Blur Input on average. Changes in sequence-mean absolute trajectory error (ATE) RMSE ranged from +0.004 to +0.051 m for ORB and from −0.008 to +0.036 m for SIFT. Seeds were averaged within each sequence before inference. No tested branch achieved a robust ATE improvement across both detectors. Pixel, raw-feature, normalized-feature, geometry-state, and trajectory endpoints produced different method rankings. These findings motivate endpoint-specific evaluation. The task experiment does not validate naturally blurred long-exposure video, a deployed simultaneous localization and mapping system, or sensor hardware.

Schlagwörter

Stichwörter der Autor:innen

ORBRichardson–Lucy deconvolutionSIFTcamera-image preprocessingmotion deblurringsensitivity analysis

Autor:innen und Institutionen

  • Department of Mechanical and Electronic Engineering, School of Mechatronics Engineering, Henan University of Science and Technology, Luoyang 471003, China.

ORCID-Profile: Runqing Xue

Förderung

  • National Natural Science Foundation of China
  • Henan University of Science and Technology
  • the Major Science and Technology Projects of Henan Province

Zitieren

APA

Ku, X., Xue, R., & Liang, Y. (2026). Feature-Level Reliability of Directional-Kernel Richardson–Lucy Deblurring Under Kernel-Length and Direction Controls. Sensors, 26(16), 5249. https://doi.org/10.3390/s26165249

Vancouver

Ku X, Xue R, Liang Y. Feature-Level Reliability of Directional-Kernel Richardson–Lucy Deblurring Under Kernel-Length and Direction Controls. Sensors. 2026;26(16):5249. doi:10.3390/s26165249

BibTeX
@article{Ku2026,
  author = {Ku, Xiangchen and Xue, Runqing and Liang, Yichen},
  title = {Feature-Level Reliability of Directional-Kernel Richardson–Lucy Deblurring Under Kernel-Length and Direction Controls},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {16},
  pages = {5249},
  doi = {10.3390/s26165249}
}
Kostenlos starten →