TTRD3通过纹理迁移与双扩散机制，提升遥感图像超分辨率质量。
TTRD3: Texture Transfer Residual Denoising Dual Diffusion Model for Remote Sensing Image Super-Resolution
- 多尺度特征聚合+稀疏纹理引导，增强细节捕捉能力。
- 相比顶尖方法，LPIPS降低1.43%，FID提升3.67%。
- 适合需要高保真遥感影像的科研与地理分析场景。
遥感图像超分辨率（RSISR）旨在从低分辨率输入重建高分辨率图像，以支持地物精细识别。现有方法面临三大挑战：（1）难以从空间异质性高的遥感场景中提取多尺度特征；（2）先验信息不足导致重建语义不一致；（3）几何精度与视觉质量间的权衡失衡。为此，本文提出纹理转移残差去噪双扩散模型（TTRD3），包含三项创新：第一，采用并行异质卷积核的多尺度特征聚合模块（MFAB），实现多尺度特征提取；第二，设计稀疏纹理转移引导模块（STTG），从相似场景参考图中迁移高分辨率纹理先验；第三，构建残差去噪双扩散框架（RDDM），结合残差扩散进行确定性重建与噪声扩散生成多样性结果。在多源遥感数据集上的实验表明，TTRD3优于当前最优方法，在LPIPS上提升1.43%，FID改善3.67%。代码与模型已开源：https://github.com/LED-666/TTRD3。
原文摘要 · Abstract (English)
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: https://github.com/LED-666/TTRD3.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。