EMR-Diff：边缘感知多模态残差扩散模型用于高光谱图像超分辨率
EMR-Diff: Edge-aware Multimodal Residual Diffusion Model for Hyperspectral Image Super-resolution
提出边缘感知噪声策略与多模态残差机制，可迁移到其他多模态融合超分任务中，利用高分辨率辅助图像的边缘信息引导扩散模型优先重建高频细节。
原文依据 Edge-aware noise strategy is designed by exploiting the edge information of HR-MSI, which guides the model to prioritize high-frequency detail reconstruction
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论硬件限制使得同时获取高空间分辨率和高光谱分辨率的高光谱图像（HSI）具有挑战性。一种有前景的解决方案是融合低分辨率HSI（LR-HSI）与高分辨率多光谱图像（HR-MSI）以生成高分辨率HSI（HR-HSI）。近期，扩散模型为HSI超分辨率带来了可能性，但存在采样效率低、生成细节有限和去噪不足的问题。为解决这些问题，我们提出了边缘感知多模态残差扩散模型（EMR-Diff）。具体而言，引入多模态残差机制以促进HR-MSI、LR-HSI和HR-HSI之间的高效信息传递，显著提升融合效率。边缘感知噪声策略通过利用HR-MSI的边缘信息设计，对边缘区域施加更强的噪声扰动，引导模型优先重建高频细节。此外，我们提出了双边注意力融合UNet并设计了多尺度监督机制，以实现光谱和空间特征的渐进重建与协同优化。大量实验表明，我们的方法在定量指标和视觉质量上均优于现有方法。
英文原文摘要 1339 字符
Hardware constraints make it challenging to simultaneously acquire hyperspectral images (HSIs) with both high spatial and high spectral resolutions. A promising solution is to fuse low-resolution HSI (LR-HSI) with high-resolution multispectral images (HR-MSI) to generate high-resolution HSI (HR-HSI). Recently, diffusion models have introduced possibilities for HSI super-resolution, but suffer from low-efficiency sampling, detail-limited generation, and insufficient denoising. To address these issues, we propose an Edge-aware Multimodal Residual Diffusion Model (EMR-Diff). Specifically, multimodal residual mechanism is introduced to facilitate efficient information transfer among HR-MSI, LR-HSI, and HR-HSI, significantly improving the fusion efficiency. Edge-aware noise strategy is designed by exploiting the edge information of HR-MSI, which guides the model to prioritize high-frequency detail reconstruction by applying stronger noise perturbations to edge regions. In addition, we propose a Bilateral Attention Fusion UNet and design a multi-scale supervision mechanism to enable progressive reconstruction and collaborative optimization of spectral and spatial features. Extensive experiments demonstrate that our method achieves superior performance over existing approaches in both quantitative metrics and visual quality.