面向不均衡纹理的遥感图像超分辨率：一种纹理感知扩散框架
Remote Sensing Image Super-Resolution for Imbalanced Textures: A Texture-Aware Diffusion Framework
把纹理密度图同时用作扩散的空间条件、损失调制和采样调度适配器，这一「先验图三用」的思路可直接迁移到其他需要抑制生成幻觉的复原任务（如医学影像、低光照增强）。
原文依据 as an explicit spatial conditioning to guide the diffusion process, as a loss modulation term to prioritize texture-rich regions, and as a dynamic adapter for the sampling schedule
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论生成式扩散先验近期在自然图像超分辨率中取得了最优性能，展现出合成逼真细节的强大能力。然而，将其直接应用于遥感图像超分辨率（RSISR）时暴露出明显不足。与自然图像不同，遥感图像呈现出独特的纹理分布：地物在全局上随机、在局部上聚集，从而导致纹理高度不均衡。这种不均衡严重阻碍了模型的空间感知能力。为解决该问题，我们提出 TexADiff，一种新颖的框架，它首先估计相对纹理密度图（RTDM）以表示纹理分布。随后，TexADiff 以三种协同方式利用该 RTDM：作为显式空间条件引导扩散过程，作为损失调制项以优先关注纹理丰富区域，以及作为采样调度的动态适配器。这些改动旨在赋予模型显式的纹理感知能力。实验表明，TexADiff 取得了更优或具有竞争力的定量指标。此外，定性结果显示，我们的模型在生成忠实的高频细节的同时有效抑制了纹理幻觉。重建质量的提升也带来了下游任务性能的显著增益。本方法的源代码可在 https://github.com/ZezFuture/TexAdiff 获取。
英文原文摘要 1485 字符
Generative diffusion priors have recently achieved state-of-the-art performance in natural image super-resolution, demonstrating a powerful capability to synthesize photorealistic details. However, their direct application to remote sensing image super-resolution (RSISR) reveals significant shortcomings. Unlike natural images, remote sensing images exhibit a unique texture distribution where ground objects are globally stochastic yet locally clustered, leading to highly imbalanced textures. This imbalance severely hinders the model's spatial perception. To address this, we propose TexADiff, a novel framework that begins by estimating a Relative Texture Density Map (RTDM) to represent the texture distribution. TexADiff then leverages this RTDM in three synergistic ways: as an explicit spatial conditioning to guide the diffusion process, as a loss modulation term to prioritize texture-rich regions, and as a dynamic adapter for the sampling schedule. These modifications are designed to endow the model with explicit texture-aware capabilities. Experiments demonstrate that TexADiff achieves superior or competitive quantitative metrics. Furthermore, qualitative results show that our model generates faithful high-frequency details while effectively suppressing texture hallucinations. This improved reconstruction quality also results in significant gains in downstream task performance. The source code of our method can be found at https://github.com/ZezFuture/TexAdiff.