Two-Level Semantic-Driven Diffusion Based Hyperspectral Pansharpening

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 f...

Full description

Saved in:
Bibliographic Details
Main Authors: Lin He, Wenrui Liang, Antonio Plaza
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10842049/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1832542607431958528
author Lin He
Wenrui Liang
Antonio Plaza
author_facet Lin He
Wenrui Liang
Antonio Plaza
author_sort Lin He
collection DOAJ
description 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.
format Article
id doaj-art-bf4a2d5a9f4443cb93bb958e4606c2e6
institution Kabale University
issn 1939-1404
2151-1535
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
spelling doaj-art-bf4a2d5a9f4443cb93bb958e4606c2e62025-02-04T00:00:23ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing1939-14042151-15352025-01-01184213422610.1109/JSTARS.2025.352999310842049Two-Level Semantic-Driven Diffusion Based Hyperspectral PansharpeningLin He0https://orcid.org/0000-0003-3801-7257Wenrui Liang1Antonio Plaza2https://orcid.org/0000-0002-9613-1659School of Automation Science and Engineering, South China University of Technology, Guangzhou, ChinaSchool of Automation Science and Engineering, South China University of Technology, Guangzhou, ChinaHyperspectral Computing Laboratory, University of Extremadura, Caceres, SpainOver 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.https://ieeexplore.ieee.org/document/10842049/Diffusion modelhyperspectral (HS) imagespansharpeningtwo-level semantics
spellingShingle Lin He
Wenrui Liang
Antonio Plaza
Two-Level Semantic-Driven Diffusion Based Hyperspectral Pansharpening
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Diffusion model
hyperspectral (HS) images
pansharpening
two-level semantics
title Two-Level Semantic-Driven Diffusion Based Hyperspectral Pansharpening
title_full Two-Level Semantic-Driven Diffusion Based Hyperspectral Pansharpening
title_fullStr Two-Level Semantic-Driven Diffusion Based Hyperspectral Pansharpening
title_full_unstemmed Two-Level Semantic-Driven Diffusion Based Hyperspectral Pansharpening
title_short Two-Level Semantic-Driven Diffusion Based Hyperspectral Pansharpening
title_sort two level semantic driven diffusion based hyperspectral pansharpening
topic Diffusion model
hyperspectral (HS) images
pansharpening
two-level semantics
url https://ieeexplore.ieee.org/document/10842049/
work_keys_str_mv AT linhe twolevelsemanticdrivendiffusionbasedhyperspectralpansharpening
AT wenruiliang twolevelsemanticdrivendiffusionbasedhyperspectralpansharpening
AT antonioplaza twolevelsemanticdrivendiffusionbasedhyperspectralpansharpening