DG²-TCR: An Adaptive Clouds Removal Network for Optical Remote Sensing Images Using SAR-Driven Dual-Flow Fusion Guidance

作者：Xianjun Gao, Jinhui Yang, Xudong Xie, Yuanwei Yang, Nan Wang, Xinran Cao, Bin Du, Meilin Tan, Lei Xu, Yuan Kou · 发表于：IEEE Transactions on Geoscience and Remote Sensing · 年份：2025 · DOI：10.1109/tgrs.2025.3557913 · 被引用次数：4 · 研究领域：Advanced Image Fusion Techniques、Infrared Target Detection Methodologies

Clouds in optical remote sensing images (ORSI) significantly limit image utilization. Traditional cloud removal methods using single or multi-temporal data sources struggle to ensure reliable reconstruction for thick cloud areas. Synthetic Aperture Radar (SAR) images are increasingly used to recover information obscured by clouds, but their performance in cloud-obscured regions is unstable. Therefore, an adaptive cloud removal network for remote sensing images, named DG2-TCR, is proposed based on SAR-driven dual-flow fusion guidance (DFG). DG2-TCR uses SAR and ORSI to construct DFG, including local spatial-spectral feature reconstruction (LSSFR) flow and global texture feature compensation (GTFC). LSSFR, driven by ORSI and SAR, efficiently extracts useful features in non-cloud areas and focuses on local information reconstruction using the designed spatial-spectral features inference reconstruction block (SSIRB). Based on SAR images, GTFC guides the compensation of global texture information. DFG can adaptively extract features and reconstruct missing information from local and global scales. The public SEN12MS-CR-TS dataset is divided into four sub-datasets with different coverage to evaluate the recovering capability in varying clouds. Experiments show that the PSNR, SSIM, RMSE, FID, and NCC indicator values on four sub-datasets and the SIMLE-CR dataset are better than the seven comparison methods. Furthermore, the ablation experiments show that the generalization and robus...