You are currently viewing a new version of our website. To view the old version click .
Remote Sensing
  • This is an early access version, the complete PDF, HTML, and XML versions will be available soon.
  • Article
  • Open Access

22 December 2025

Shift-Invariant Unsupervised Pansharpening Based on Diffusion Model

,
,
,
,
,
and
1
Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, China
2
School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences, Beijing 100049, China
3
Key Laboratory of Technology in Geo-Spatial Information Processing and Application System, Chinese Academy of Sciences, Beijing 100190, China
4
Institute of Remote Sensing Application in Public Security, People’s Public Security University of China, Beijing 100038, China
Remote Sens.2026, 18(1), 27;https://doi.org/10.3390/rs18010027 
(registering DOI)
This article belongs to the Section Remote Sensing Image Processing

Abstract

Pansharpening is a crucial topic in remote sensing, and numerous deep learning-based methods have recently been proposed to explore the potential of deep neural networks (DNNs). However, existing approaches are often sensitive to spatial translation errors between high-resolution panchromatic (HRPan) and low-resolution multispectral (LRMS) images, leading to noticeable artifacts in the fused results. To address this issue, we propose an unsupervised pansharpening method that is robust to translation misalignment between HRPan and LRMS inputs. The proposed framework integrates a shift-invariant module to estimate subpixel spatial offsets and a diffusion-based generative model to progressively enhance spatial and spectral details. Moreover, a multi-scale detail injection module is designed to guide the diffusion process with fine-grained structural information. In addition, a carefully formulated loss function is established to preserve the fidelity of fusion results and facilitate the estimation of translation errors. Experiments conducted on the GaoFen-2, GaoFen-1, and WorldView-2 datasets demonstrate that the proposed method achieves superior fusion quality compared with state-of-the-art approaches and effectively suppresses artifacts caused by translation errors.

Article Metrics

Citations

Article Access Statistics

Multiple requests from the same IP address are counted as one view.