用扩散先验和多模态约束，高效提升遥感图像分辨率以更好识别作物类型。
An Efficient Remote Sensing Super Resolution Method Exploring Diffusion Priors and Multi-Modal Constraints for Crop Type Mapping
- 基于冻结的Stable Diffusion，融合多模态信息实现高效超分辨率重建。
- 在RGB和IR波段分别达32.63/0.84和23.99/0.78的性能，NDVI误差仅0.042。
- 推理仅需0.39秒/图，且在农作物分类任务中表现优于原生影像。
超分辨率技术可挖掘历史中低分辨率遥感影像的价值。尽管生成模型特别是扩散模型被用于遥感超分辨率（RSSR），但仍面临训练成本高、推理慢、辅助信息利用不足及下游任务评估缺失等问题。本文提出一种高效轻量级框架LSSR，依托新构建的配对30米Landsat 8与10米Sentinel-2多模态数据集。该框架基于预训练冻结的Stable Diffusion，通过跨模态注意力融合数字高程模型、土地覆盖和月份等辅助信息，并引入合成孔径雷达引导，结合适配器与定制傅里叶NDVI损失，平衡空间细节与光谱保真度。大量实验表明，LSSR显著改善作物边界识别与恢复能力，在RGB与近红外波段分别取得32.63/0.84与23.99/0.78的峰值信噪比/结构相似性指标，NDVI均方误差最低达0.042，同时保持0.39秒/图的高效推理速度。此外，其在NASA HLS数据上的迁移表现优于原生Sentinel-2，作物分类F1得分达0.86，验证了其在精准农业中的应用潜力。
原文摘要 · Abstract (English)
Super resolution offers a way to harness medium even lowresolution but historically valuable remote sensing image archives. Generative models, especially diffusion models, have recently been applied to remote sensing super resolution (RSSR), yet several challenges exist. First, diffusion models are effective but require expensive training from scratch resources and have slow inference speeds. Second, current methods have limited utilization of auxiliary information as real-world constraints to reconstruct scientifically realistic images. Finally, most current methods lack evaluation on downstream tasks. In this study, we present a efficient LSSR framework for RSSR, supported by a new multimodal dataset of paired 30 m Landsat 8 and 10 m Sentinel 2 imagery. Built on frozen pretrained Stable Diffusion, LSSR integrates crossmodal attention with auxiliary knowledge (Digital Elevation Model, land cover, month) and Synthetic Aperture Radar guidance, enhanced by adapters and a tailored Fourier NDVI loss to balance spatial details and spectral fidelity. Extensive experiments demonstrate that LSSR significantly improves crop boundary delineation and recovery, achieving state-of-the-art performance with Peak Signal-to-Noise Ratio/Structural Similarity Index Measure of 32.63/0.84 (RGB) and 23.99/0.78 (IR), and the lowest NDVI Mean Squared Error (0.042), while maintaining efficient inference (0.39 sec/image). Moreover, LSSR transfers effectively to NASA Harmonized Landsat and Sentinel (HLS) super resolution, yielding more reliable crop classification (F1: 0.86) than Sentinel-2 (F1: 0.85). These results highlight the potential of RSSR to advance precision agriculture.
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。