DESAT: A Distance-Enhanced Strip Attention Transformer for Remote Sensing Image Super-Resolution

Transformer-based methods have demonstrated impressive performance in image super-resolution tasks. However, when applied to large-scale Earth observation images, the existing transformers encounter two significant challenges: (1) insufficient consideration of spatial correlation between adjacent gr...

Full description

Saved in:
Bibliographic Details
Main Authors: Yujie Mao, Guojin He, Guizhou Wang, Ranyu Yin, Yan Peng, Bin Guan
Format: Article
Language:English
Published: MDPI AG 2024-11-01
Series:Remote Sensing
Subjects:
Online Access:https://www.mdpi.com/2072-4292/16/22/4251
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850226563960799232
author Yujie Mao
Guojin He
Guizhou Wang
Ranyu Yin
Yan Peng
Bin Guan
author_facet Yujie Mao
Guojin He
Guizhou Wang
Ranyu Yin
Yan Peng
Bin Guan
author_sort Yujie Mao
collection DOAJ
description Transformer-based methods have demonstrated impressive performance in image super-resolution tasks. However, when applied to large-scale Earth observation images, the existing transformers encounter two significant challenges: (1) insufficient consideration of spatial correlation between adjacent ground objects; and (2) performance bottlenecks due to the underutilization of the upsample module. To address these issues, we propose a novel distance-enhanced strip attention transformer (DESAT). The DESAT integrates distance priors, easily obtainable from remote sensing images, into the strip window self-attention mechanism to capture spatial correlations more effectively. To further enhance the transfer of deep features into high-resolution outputs, we designed an attention-enhanced upsample block, which combines the pixel shuffle layer with an attention-based upsample branch implemented through the overlapping window self-attention mechanism. Additionally, to better simulate real-world scenarios, we constructed a new cross-sensor super-resolution dataset using Gaofen-6 satellite imagery. Extensive experiments on both simulated and real-world remote sensing datasets demonstrate that the DESAT outperforms state-of-the-art models by up to 1.17 dB along with superior qualitative results. Furthermore, the DESAT achieves more competitive performance in real-world tasks, effectively balancing spatial detail reconstruction and spectral transform, making it highly suitable for practical remote sensing super-resolution applications.
format Article
id doaj-art-eb27d84f61c14123be732fe76e46eed2
institution OA Journals
issn 2072-4292
language English
publishDate 2024-11-01
publisher MDPI AG
record_format Article
series Remote Sensing
spelling doaj-art-eb27d84f61c14123be732fe76e46eed22025-08-20T02:05:02ZengMDPI AGRemote Sensing2072-42922024-11-011622425110.3390/rs16224251DESAT: A Distance-Enhanced Strip Attention Transformer for Remote Sensing Image Super-ResolutionYujie Mao0Guojin He1Guizhou Wang2Ranyu Yin3Yan Peng4Bin Guan5Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, ChinaAerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, ChinaAerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, ChinaAerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, ChinaAerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, ChinaSchool of Remote Sensing and Information Engineering, Wuhan University, Wuhan 430079, ChinaTransformer-based methods have demonstrated impressive performance in image super-resolution tasks. However, when applied to large-scale Earth observation images, the existing transformers encounter two significant challenges: (1) insufficient consideration of spatial correlation between adjacent ground objects; and (2) performance bottlenecks due to the underutilization of the upsample module. To address these issues, we propose a novel distance-enhanced strip attention transformer (DESAT). The DESAT integrates distance priors, easily obtainable from remote sensing images, into the strip window self-attention mechanism to capture spatial correlations more effectively. To further enhance the transfer of deep features into high-resolution outputs, we designed an attention-enhanced upsample block, which combines the pixel shuffle layer with an attention-based upsample branch implemented through the overlapping window self-attention mechanism. Additionally, to better simulate real-world scenarios, we constructed a new cross-sensor super-resolution dataset using Gaofen-6 satellite imagery. Extensive experiments on both simulated and real-world remote sensing datasets demonstrate that the DESAT outperforms state-of-the-art models by up to 1.17 dB along with superior qualitative results. Furthermore, the DESAT achieves more competitive performance in real-world tasks, effectively balancing spatial detail reconstruction and spectral transform, making it highly suitable for practical remote sensing super-resolution applications.https://www.mdpi.com/2072-4292/16/22/4251remote sensingimage super-resolutiondeep learningtransformerself-attentionGaofen-6 satellite
spellingShingle Yujie Mao
Guojin He
Guizhou Wang
Ranyu Yin
Yan Peng
Bin Guan
DESAT: A Distance-Enhanced Strip Attention Transformer for Remote Sensing Image Super-Resolution
Remote Sensing
remote sensing
image super-resolution
deep learning
transformer
self-attention
Gaofen-6 satellite
title DESAT: A Distance-Enhanced Strip Attention Transformer for Remote Sensing Image Super-Resolution
title_full DESAT: A Distance-Enhanced Strip Attention Transformer for Remote Sensing Image Super-Resolution
title_fullStr DESAT: A Distance-Enhanced Strip Attention Transformer for Remote Sensing Image Super-Resolution
title_full_unstemmed DESAT: A Distance-Enhanced Strip Attention Transformer for Remote Sensing Image Super-Resolution
title_short DESAT: A Distance-Enhanced Strip Attention Transformer for Remote Sensing Image Super-Resolution
title_sort desat a distance enhanced strip attention transformer for remote sensing image super resolution
topic remote sensing
image super-resolution
deep learning
transformer
self-attention
Gaofen-6 satellite
url https://www.mdpi.com/2072-4292/16/22/4251
work_keys_str_mv AT yujiemao desatadistanceenhancedstripattentiontransformerforremotesensingimagesuperresolution
AT guojinhe desatadistanceenhancedstripattentiontransformerforremotesensingimagesuperresolution
AT guizhouwang desatadistanceenhancedstripattentiontransformerforremotesensingimagesuperresolution
AT ranyuyin desatadistanceenhancedstripattentiontransformerforremotesensingimagesuperresolution
AT yanpeng desatadistanceenhancedstripattentiontransformerforremotesensingimagesuperresolution
AT binguan desatadistanceenhancedstripattentiontransformerforremotesensingimagesuperresolution