Two-Level Semantic-Driven Diffusion Based Hyperspectral Pansharpening

作     者：He, Lin Liang, Wenrui Plaza, Antonio 

作者机构：South China Univ Technol Sch Automat Sci & Engn Guangzhou 510640 Peoples R China South China Univ Technol Guangdong Engn Technol Res Ctr Unmanned Aerial Veh Guangzhou 510640 Peoples R China Minist Educ PRC Key Lab Autonomous Syst & Networked Control Guangzhou 510640 Peoples R China Univ Extremadura Hyperspectral Comp Lab Caceres 10003 Spain 

出 版 物：《IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING》 (IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens.)

年 卷 期：2025年第18卷

页      面：4213-4226页

核心收录：

学科分类：0808[工学-电气工程] 1002[医学-临床医学] 08[工学] 0705[理学-地理学] 0816[工学-测绘科学与技术] 

基　　金：National Natural Science Foundation of China Guangdong Basic and Applied Basic Research Foundation [2022A1515011615, 2023A1515011887] 

主　　题：Semantics Pansharpening Noise reduction Feature extraction Noise Diffusion models Image restoration Decoding Cognition Training Diffusion model hyperspectral (HS) images pansharpening two-level semantics 

摘      要：Over recent years, denoising diffusion probabilistic models (DDPMs) have received many attentions due to their powerful ability to infer data distribution. However, most of existing DDPM-based hyperspectral (HS) pansharpening methods over rely on local processing to perform recovery, which usually fails to reconcile global contextual semantics and local details in data. To address the issue, we propose a two-level semantic-driven diffusion method for HS pansharpening. In our method, we first extract semantics in two levels, where the low-level semantic not only leads the extraction of conditional details, but also supports the further semantic extraction while the high-level semantic is related to scene cognition. Then, the features from both the low-level and high-level semantics are conditionally injected to the denoising network to guide the high-resolution HS recovery. Experiments on multiple datasets verify the effectiveness of our method.