CLEAR: A Fast Cloud Removal Method for Optical Remote Sensing Images Combining Class-Based Linear Regression and Iterative Residual Compensation
- 12 January 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 64 (01962892) , 1-16
Abstract
Cloud and cloud shadow contamination significantly reduce the applicability of optical remote sensing images, introducing relevant gaps in land-cover representation. Existing cloud removal methods usually do not achieve both high accuracy and high computational efficiency, limiting their effectiveness in real applications. In this paper, we propose a fast and effective method named Class-based Linear rEgression and iterAtive Residual compensation (CLEAR) to fill gaps in optical images. In the class-based linear regression step, CLEAR first classifies the stacked time-series reference images to effectively characterizes the land-cover dynamics. It then preliminarily fills gaps by establishing the relationship between the reference images and the target cloudy image. The iterative residual compensation step further improves the cloud removal accuracy for each target cloudy pixel by integrating the residuals of its neighboring similar pixels. The similar pixel selection is achieved by a novel K-D tree-based approach. The performance of CLEAR was compared with seven representative cloud removal methods using simulated cloudy images with different cloud covers at three study sites. The experimental results demonstrate that CLEAR outperformed other methods by obtaining the highest prediction accuracies and preserving better spatial details in the cloud-removed images. Moreover, CLEAR also presented higher computational efficiency compared to the other methods. We also demonstrate CLEAR’s potential in supporting agricultural and large-scale remote sensing applications. The Python code of CLEAR and the experimental dataset are available at https://github.com/HoucaiGuo/CLEAR-code.Keywords
Funding Information
- China Scholarship Council (202306860011)
- European Space Agency (4000125259/18/I-NB–(CUP))
- European Space Agency (E63C23002010006)
This publication has 48 references indexed in Scilit:
- Generative networks for spatio-temporal gap filling of Sentinel-2 reflectancesISPRS Journal of Photogrammetry and Remote Sensing, 2025
- Assessment of Machine Learning Algorithms for Land Cover Classification in a Complex Mountainous LandscapeJournal of Geovisualization and Spatial Analysis, 2024
- Training-free thick cloud removal for Sentinel-2 imagery using value propagation interpolationISPRS Journal of Photogrammetry and Remote Sensing, 2024
- Urban Tree Species Classification Using UAV-Based Multispectral Images and LiDAR Point CloudsJournal of Geovisualization and Spatial Analysis, 2023
- A robust and unified land surface phenology algorithm for diverse biomes and growth cycles in China by using harmonized Landsat and Sentinel-2 imageryISPRS Journal of Photogrammetry and Remote Sensing, 2023
- Cloud and cloud shadow detection for optical satellite imagery: Features, algorithms, validation, and prospectsISPRS Journal of Photogrammetry and Remote Sensing, 2022
- 10 m crop type mapping using Sentinel-2 reflectance and 30 m cropland data layer productInternational Journal of Applied Earth Observation and Geoinformation, 2022
- Filling gaps in Landsat ETM+ SLC-off images with Sentinel-2 MSI imagesInternational Journal of Applied Earth Observation and Geoinformation, 2021
- Object-based cloud and cloud shadow detection in Landsat imageryRemote Sensing of Environment, 2012
- A simple and effective method for filling gaps in Landsat ETM+ SLC-off imagesRemote Sensing of Environment, 2011