EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Consistency-Guided Collaborative Filtering Framework for Suppressing Structured Coherent Artifacts

Rui Wang, Peizhen Zhang, Canping Li, Hairong Zhang, Xiangbo Gong, Bin Hu

Remote Sensing · 17.08.2026 · 18 (16) · 2780

DOI: 10.3390/rs18162780 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 17.08.2026. Verfasst von Rui Wang und 5 weiteren Autor:innen. Die Arbeit nennt 48 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Zhanjiang Municipal Special Project for Marine Youth Talent Innovation, Deep Earth Probe and Mineral Resources Exploration-National Science and Technology Major Project, Special Fund of Key Laboratory of Geoghysical Exploration Equipment, Ministry of Education.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Indirect observation systems, such as hyperspectral remote sensing and passive geophysical measurements, retrieve useful information from redundant observations of the same scene. However, the resulting data are often contaminated by structured coherent artifacts caused by sensor nonuniformity, calibration residuals, or incomplete illumination. These artifacts are difficult to suppress because they are spatially organized components with directional continuity and non-negligible correlation. Their signal-like coherence allows them to mimic image textures or physical events, making conventional denoising methods prone to residual artifacts or signal leakage. To address this problem, we propose a consistency-guided collaborative filtering framework for suppressing structured coherent artifacts while preserving useful signals. The proposed framework extends paired-observation similarity analysis into a consistency-guided strategy for redundant observations. Paired observations of the same target are constructed to distinguish useful signals from physically inconsistent artifacts. This consistency contrast is incorporated into collaborative filtering to guide block matching and aggregation, while a coherent noise power spectral density model characterizes the directional and spatial correlation of the artifacts for targeted noise shrinkage. The proposed framework is evaluated primarily on hyperspectral remote-sensing images contaminated by simulated stripe artifacts, with additional validation on synthetic and field geophysical paired-observation data containing nonphysical coherent events. The results demonstrate that the proposed method can suppress structured coherent artifacts while preserving useful signals and maintaining high signal fidelity. This work provides a unified way to exploit observational redundancy for enhancing imaging reliability.

Förderung

  • Zhanjiang Municipal Special Project for Marine Youth Talent Innovation
  • Deep Earth Probe and Mineral Resources Exploration-National Science and Technology Major Project
  • Special Fund of Key Laboratory of Geoghysical Exploration Equipment, Ministry of Education
  • Guangdong Association for Science and Technology Youth Science and Technology Talent Cultivation Program
  • Guangdong Basic and Applied Basic Research Foundation
  • Program for Scientific Research start-up funds of Guangdong Ocean University

Zitieren

APA

Wang, R., Zhang, P., Li, C., Zhang, H., Gong, X., & Hu, B. (2026). A Consistency-Guided Collaborative Filtering Framework for Suppressing Structured Coherent Artifacts. Remote Sensing, 18(16), 2780. https://doi.org/10.3390/rs18162780

Vancouver

Wang R, Zhang P, Li C, Zhang H, Gong X, Hu B. A Consistency-Guided Collaborative Filtering Framework for Suppressing Structured Coherent Artifacts. Remote Sensing. 2026;18(16):2780. doi:10.3390/rs18162780

BibTeX
@article{Wang2026,
  author = {Wang, Rui and Zhang, Peizhen and Li, Canping and Zhang, Hairong and Gong, Xiangbo and Hu, Bin},
  title = {A Consistency-Guided Collaborative Filtering Framework for Suppressing Structured Coherent Artifacts},
  journal = {Remote Sensing},
  year = {2026},
  volume = {18},
  number = {16},
  pages = {2780},
  doi = {10.3390/rs18162780}
}
Kostenlos starten →