Remote Sensing Image Super-Resolution (RSISR) reconstructs high-resolution (HR) remote sensing images from low-resolution inputs to support fine-grained ground object interpretation. Existing methods face three key challenges: (1) Difficulty in extracting multi-scale features from spatially heterogeneous RS scenes, (2) Limited prior information causing semantic inconsistency in reconstructions, and (3) Trade-off imbalance between geometric accuracy and visual quality. To address these issues, we propose the Texture Transfer Residual Denoising Dual Diffusion Model (TTRD3) with three innovations: First, a Multi-scale Feature Aggregation Block (MFAB) employing parallel heterogeneous convolutional kernels for multi-scale feature extraction. Second, a Sparse Texture Transfer Guidance (STTG) module that transfers HR texture priors from reference images of similar scenes. Third, a Residual Denoising Dual Diffusion Model (RDDM) framework combining residual diffusion for deterministic reconstruction and noise diffusion for diverse generation. Experiments on multi-source RS datasets demonstrate TTRD3's superiority over state-of-the-art methods, achieving 1.43% LPIPS improvement and 3.67% FID enhancement compared to best-performing baselines. Code/model:this https URL.
View on arXiv@article{liu2025_2504.13026,
title={ TTRD3: Texture Transfer Residual Denoising Dual Diffusion Model for Remote Sensing Image Super-Resolution },
author={ Yide Liu and Haijiang Sun and Xiaowen Zhang and Qiaoyuan Liu and Zhouchang Chen and Chongzhuo Xiao },
journal={arXiv preprint arXiv:2504.13026},
year={ 2025 }
}