EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Diffusion-Driven Relative Radiometric Normalization with Spatial–Spectral Attention Residual Network for Multi-Temporal Remote Sensing Imagery

Liyao Song, Chunyan Liu, Jiaqi Ma, Haiwei Li, Long Ma, Ruofeng Wang

Remote Sensing · 03.07.2026 · 18 (13) · 2156

DOI: 10.3390/rs18132156 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 03.07.2026. Verfasst von Liyao Song und 5 weiteren Autor:innen. Die Arbeit nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National The Key Research and Development Program of China, General Special Scientific Research Program Project of the Shaanxi Provincial Department of Education, Natural Science Foundation of Shaanxi Province.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Relative radiometric normalization (RRN) is fundamental to multi-temporal remote sensing analysis; however, conventional techniques often struggle with nonlinear distortions, outlier contamination, and heterogeneous land-cover conditions. To address these challenges, we propose a diffusion-based probabilistic framework that models radiometric inconsistency as a combination of deterministic residuals and stochastic perturbations. In this framework, the forward process injects structured noise and stochastic perturbations, while the reverse process restores radiometric consistency through a dual-objective variational formulation. At the core of this framework is a spatial–spectral attention residual network (SSARN), which integrates residual learning with dual attention mechanisms to capture cross-band dependencies and multi-scale spatial context. A preprocessing stage guided by the structural similarity index (SSIM) further enhances robustness by automatically selecting stable pseudo-invariant regions for model training. Comprehensive experiments on multi-temporal Sentinel-2 datasets demonstrate that the proposed method consistently outperforms existing approaches, achieving higher accuracy and enhanced spectral fidelity. Moreover, the framework ensures greater consistency of the normalized difference vegetation index (NDVI) and preserves fine-grained textural details, underscoring its potential as a scalable and resilient solution for large-scale RRN in remote sensing applications.

Förderung

  • National The Key Research and Development Program of China
  • General Special Scientific Research Program Project of the Shaanxi Provincial Department of Education
  • Natural Science Foundation of Shaanxi Province
  • Open Research Fund of Shaanxi Key Laboratory of Optical Remote Sensing and Intelligent Information Processing
  • 2024 Provincial-Level Approval of College Students’ Innovation Program Project
  • Xi’an Natural Science Foundation Project–General Program

Zitieren

APA

Song, L., Liu, C., Ma, J., Li, H., Ma, L., & Wang, R. (2026). Diffusion-Driven Relative Radiometric Normalization with Spatial–Spectral Attention Residual Network for Multi-Temporal Remote Sensing Imagery. Remote Sensing, 18(13), 2156. https://doi.org/10.3390/rs18132156

Vancouver

Song L, Liu C, Ma J, Li H, Ma L, Wang R. Diffusion-Driven Relative Radiometric Normalization with Spatial–Spectral Attention Residual Network for Multi-Temporal Remote Sensing Imagery. Remote Sensing. 2026;18(13):2156. doi:10.3390/rs18132156

BibTeX
@article{Song2026,
  author = {Song, Liyao and Liu, Chunyan and Ma, Jiaqi and Li, Haiwei and Ma, Long and Wang, Ruofeng},
  title = {Diffusion-Driven Relative Radiometric Normalization with Spatial–Spectral Attention Residual Network for Multi-Temporal Remote Sensing Imagery},
  journal = {Remote Sensing},
  year = {2026},
  volume = {18},
  number = {13},
  pages = {2156},
  doi = {10.3390/rs18132156}
}
Kostenlos starten →