Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Chen, Yiheng, Ma, Zihui, Jiang, Peishi, Dai, Yilong, Hu, Qikai, Ye, Xinyue, Li, Lingyao, Sousa, Rita, Yu, Runlong
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2604.16841
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866914486031482880
author Chen, Yiheng
Ma, Zihui
Jiang, Peishi
Dai, Yilong
Hu, Qikai
Ye, Xinyue
Li, Lingyao
Sousa, Rita
Yu, Runlong
author_facet Chen, Yiheng
Ma, Zihui
Jiang, Peishi
Dai, Yilong
Hu, Qikai
Ye, Xinyue
Li, Lingyao
Sousa, Rita
Yu, Runlong
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2604_16841
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle When Earth Foundation Models Meet Diffusion: An Application to Land Surface Temperature Super-Resolution
Chen, Yiheng
Ma, Zihui
Jiang, Peishi
Dai, Yilong
Hu, Qikai
Ye, Xinyue
Li, Lingyao
Sousa, Rita
Yu, Runlong
Computer Vision and Pattern Recognition
Machine Learning
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.
title When Earth Foundation Models Meet Diffusion: An Application to Land Surface Temperature Super-Resolution
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2604.16841