武汉大学—童晗 |《测绘学报(英文版)》“对地观测光谱成像”专刊佳文推荐

2026-10-08 20:38:38

🔷Title l 题目

Unsupervised Pansharpening Method Based on Guided Diffusion with Degradation Constraints

🔷Citation l 引文格式TONG Han, DU Chenxi, WAN Yu, et al. Unsupervised Pansharpening Method Based on Guided Diffusion with Degradation Constraints[J]. Journal of Geodesy and Geoinformation Science, 2025, 8(4): 56-71. DOI： 10.11947/j.JGGS.2025.0405.

🔷Abstract l 摘要

The poor spatial resolution of Multispectral Image (MSI) limits its application in real world. Many deep learning-based methods perform supervised training in a reduced-resolution domain, which leads to inaccurate results. In this regard, we design an unsupervised pansharpening framework based on a guided diffusion model. Specifically, we introduce the low-resolution image pairs and degradation relationship in a priori form into the reverse diffusion step. Utilizing the pre-trained guided diffusion model to obtain the initial fused image, and then employ multi-scale and cross attention mechanism to refine the detailed information. Degradation Learning Net (DLN) accurately captures degradation relationships between image pairs. In order to produce more natural results, gradient loss and degradation loss are introduced to guide the network training. The experimental results show that our method achieves the best results in both visual and quantitative assessment compared to the current state-of-the-art unsupervised image fusion methods.

🔷Key Words l 关键词

remote sensing image; pansharpening; unsupervised learning; diffusion model

🔷Authors l 作者

TONG Han, DU Chenxi, WAN Yu, LI Jie, YUAN Qiangqiang

🔷全文摘录如下