Land surface temperature (LST) super-resolution is important for environmental monitoring. However, it remains challenging as coarse thermal observations severely underdetermine fine-scale structure. In this paper, we propose Earth Foundation Model-guided Diffusion (EFDiff), a novel framework for super-resolution under extreme spatial degradation. EFDiff uses the Prithvi-EO-2.0 Earth foundation model to encode high-resolution multispectral reflectance into geospatial embeddings, which are injected into the denoising network via cross-attention to guide fine-scale reconstruction from highly degraded observations. We study two variants, EFDiff-$ε$ and EFDiff-$x_0$, which offer complementary trade-offs between perceptual realism and pixel-level fidelity. We evaluate EFDiff under an extreme $32\times$ scale gap using a globally diverse benchmark comprising 242,416 co-registered Landsat thermal-reflectance patches. Results show that EFDiff consistently outperforms baseline methods and that cross-attention conditioning by EFM is more effective than HLS channel concatenation. Although we present EFDiff in the context of LST super-resolution, the framework is broadly applicable to remote sensing problems in which pretrained geospatial representations can guide generative reconstruction.
30m resolution Global Annual Burned Area Mapping based on Landsat images and Google Earth Engine
Institute of Remote Sensing and Digital Earth, Chinese Academy of Sciences(中国科学院遥感与数字地球研究所);Hainan Key Laboratory for Earth Observation(海南省地球观测重点实验室);China University of Mining and Technology(中国矿业大学)
Impacts of Color and Texture Distortions on Earth Observation Data in Deep Learning
RISE Research Institutes of Sweden(瑞典RISE研究院);Centre for Mathematical Sciences, Lund University(隆德大学数学科学中心);KTH Royal Institute of Technology(瑞典皇家理工学院);Swedish Centre for Impacts of Climate Extremes (climes)(瑞典气候极端影响中心)
Is sub-metre resolution necessary for cocoa mapping? A landscape-stratified evaluation of very high resolution imagery, decametric Earth Observation inputs, and operational products in Cote d'Ivoire
Democratizing planetary-scale analysis: An ultra-lightweight Earth embedding database for accurate and flexible global land monitoring
The University of Hong Kong(香港大学);Pengcheng Laboratory(鹏城实验室);Tsinghua University(清华大学);The Hong Kong Polytechnic University(香港理工大学);Tsinghua Shenzhen International Graduate School(清华大学深圳国际研究生院);Sun Yat-sen University(中山大学)
SSL4EO-L: Datasets and Foundation Models for Landsat Imagery
University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校);Technical University of Munich(慕尼黑工业大学);University of Texas at San Antonio(德克萨斯大学圣安东尼奥分校);German Aerospace Center(德国航空航天中心);Microsoft AI for Good Research Lab(微软人工智能向善研究实验室)
Semi-Supervised Semantic Segmentation in Earth Observation: The MiniFrance Suite, Dataset Analysis and Multi-task Network Study
ONERA(法国国家航空航天研究院);Université Paris-Saclay(巴黎萨克雷大学);Université Bretagne Sud(南布列塔尼大学);IRISA(布列塔尼国立高等电信学校计算机科学研究所);European Space Agency(欧洲空间局);Conservatoire national des arts et métiers(法国国立工艺学院);CEDRIC(计算机科学、电子学与自动化研究中心)