Metadata, Wavelet, and Time Aware Diffusion Models for Satellite Image Super Resolution

TL;DR

This paper introduces MWT-Diff, a novel satellite image super-resolution framework that combines diffusion models with wavelet transforms and metadata-aware encoding to enhance high-resolution remote sensing imagery.

Contribution

It presents a new metadata-, wavelet-, and time-aware encoder integrated with diffusion models for improved satellite image super-resolution.

Findings

Demonstrated superior performance over recent methods on multiple datasets.

Achieved high perceptual quality as measured by FID and LPIPS metrics.

Effectively preserves spatial details and spectral components in reconstructed images.

Abstract

The acquisition of high-resolution satellite imagery is often constrained by the spatial and temporal limitations of satellite sensors, as well as the high costs associated with frequent observations. These challenges hinder applications such as environmental monitoring, disaster response, and agricultural management, which require fine-grained and high-resolution data. In this paper, we propose MWT-Diff, an innovative framework for satellite image super-resolution (SR) that combines latent diffusion models with wavelet transforms to address these challenges. At the core of the framework is a novel metadata-, wavelet-, and time-aware encoder (MWT-Encoder), which generates embeddings that capture metadata attributes, multi-scale frequency information, and temporal relationships. The embedded feature representations steer the hierarchical diffusion dynamics, through which the model progressively reconstructs high-resolution satellite imagery from low-resolution inputs. This process preserves critical spatial characteristics including textural patterns, boundary discontinuities, and high-frequency spectral components essential for detailed remote sensing analysis. The comparative analysis of MWT-Diff across multiple datasets demonstrated favorable performance compared to recent approaches, as measured by standard perceptual quality metrics including FID and LPIPS. The code is available at https://github.com/LuigiSigillo/MWT-Diff