An Efficient Remote Sensing Super Resolution Method Exploring Diffusion Priors and Multi-Modal Constraints for Crop Type Mapping

TL;DR

This paper introduces an efficient remote sensing super resolution framework that leverages diffusion priors and multi-modal constraints, significantly improving crop mapping accuracy while maintaining fast inference speeds.

Contribution

The study presents a novel LSSR framework built on pretrained Stable Diffusion, integrating multi-modal auxiliary data and tailored loss functions for enhanced remote sensing image super resolution.

Findings

Achieves state-of-the-art super resolution metrics (PSNR/SSIM) for RGB and IR images.

Significantly improves crop boundary delineation and spectral fidelity.

Enables effective transfer to NASA HLS data for better crop classification.

Abstract

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.