Multi-Scale Long- and Short-Range Structure Aggregation Learning for Low-Illumination Remote Sensing Imagery Enhancement

Profiting from the surprising non-linear expressive capacity, deep convolutional neural networks have inspired lots of progress in low illumination (LI) remote sensing image enhancement. The key lies in sufficiently exploiting both the specific long-range (e.g., non-local similarity) and short-range...

Full description

Saved in:
Bibliographic Details
Main Authors: Yu Cao, Yuyuan Tian, Xiuqin Su, Meilin Xie, Wei Hao, Haitao Wang, Fan Wang
Format: Article
Language:English
Published: MDPI AG 2025-01-01
Series:Remote Sensing
Subjects:
Online Access:https://www.mdpi.com/2072-4292/17/2/242
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1832587608613453824
author Yu Cao
Yuyuan Tian
Xiuqin Su
Meilin Xie
Wei Hao
Haitao Wang
Fan Wang
author_facet Yu Cao
Yuyuan Tian
Xiuqin Su
Meilin Xie
Wei Hao
Haitao Wang
Fan Wang
author_sort Yu Cao
collection DOAJ
description Profiting from the surprising non-linear expressive capacity, deep convolutional neural networks have inspired lots of progress in low illumination (LI) remote sensing image enhancement. The key lies in sufficiently exploiting both the specific long-range (e.g., non-local similarity) and short-range (e.g., local continuity) structures distributed across different scales of each input LI image to build an appropriate deep mapping function from the LI images to their corresponding high-quality counterparts. However, most existing methods can only individually exploit the general long-range or short-range structures shared across most images at a single scale, thus limiting their generalization performance in challenging cases. We propose a multi-scale long–short range structure aggregation learning network for remote sensing imagery enhancement. It features flexible architecture for exploiting features at different scales of the input low illumination (LI) image, with branches including a short-range structure learning module and a long-range structure learning module. These modules extract and combine structural details from the input image at different scales and cast them into pixel-wise scale factors to enhance the image at a finer granularity. The network sufficiently leverages the specific long-range and short-range structures of the input LI image for superior enhancement performance, as demonstrated by extensive experiments on both synthetic and real datasets.
format Article
id doaj-art-f090f78838124ae8bcb102d32683ed3f
institution Kabale University
issn 2072-4292
language English
publishDate 2025-01-01
publisher MDPI AG
record_format Article
series Remote Sensing
spelling doaj-art-f090f78838124ae8bcb102d32683ed3f2025-01-24T13:47:50ZengMDPI AGRemote Sensing2072-42922025-01-0117224210.3390/rs17020242Multi-Scale Long- and Short-Range Structure Aggregation Learning for Low-Illumination Remote Sensing Imagery EnhancementYu Cao0Yuyuan Tian1Xiuqin Su2Meilin Xie3Wei Hao4Haitao Wang5Fan Wang6Key Laboratory of Space Precision Measurement Technology, Xi’an Institute of Optics and Precision Mechanics, Chinese Academy of Sciences, Xi’an 710119, ChinaKey Laboratory of Space Precision Measurement Technology, Xi’an Institute of Optics and Precision Mechanics, Chinese Academy of Sciences, Xi’an 710119, ChinaKey Laboratory of Space Precision Measurement Technology, Xi’an Institute of Optics and Precision Mechanics, Chinese Academy of Sciences, Xi’an 710119, ChinaKey Laboratory of Space Precision Measurement Technology, Xi’an Institute of Optics and Precision Mechanics, Chinese Academy of Sciences, Xi’an 710119, ChinaKey Laboratory of Space Precision Measurement Technology, Xi’an Institute of Optics and Precision Mechanics, Chinese Academy of Sciences, Xi’an 710119, ChinaKey Laboratory of Space Precision Measurement Technology, Xi’an Institute of Optics and Precision Mechanics, Chinese Academy of Sciences, Xi’an 710119, ChinaKey Laboratory of Space Precision Measurement Technology, Xi’an Institute of Optics and Precision Mechanics, Chinese Academy of Sciences, Xi’an 710119, ChinaProfiting from the surprising non-linear expressive capacity, deep convolutional neural networks have inspired lots of progress in low illumination (LI) remote sensing image enhancement. The key lies in sufficiently exploiting both the specific long-range (e.g., non-local similarity) and short-range (e.g., local continuity) structures distributed across different scales of each input LI image to build an appropriate deep mapping function from the LI images to their corresponding high-quality counterparts. However, most existing methods can only individually exploit the general long-range or short-range structures shared across most images at a single scale, thus limiting their generalization performance in challenging cases. We propose a multi-scale long–short range structure aggregation learning network for remote sensing imagery enhancement. It features flexible architecture for exploiting features at different scales of the input low illumination (LI) image, with branches including a short-range structure learning module and a long-range structure learning module. These modules extract and combine structural details from the input image at different scales and cast them into pixel-wise scale factors to enhance the image at a finer granularity. The network sufficiently leverages the specific long-range and short-range structures of the input LI image for superior enhancement performance, as demonstrated by extensive experiments on both synthetic and real datasets.https://www.mdpi.com/2072-4292/17/2/242low-illumination remote sensing image enhancementmulti-scale long- and short-range structure aggregation learningdynamic networks
spellingShingle Yu Cao
Yuyuan Tian
Xiuqin Su
Meilin Xie
Wei Hao
Haitao Wang
Fan Wang
Multi-Scale Long- and Short-Range Structure Aggregation Learning for Low-Illumination Remote Sensing Imagery Enhancement
Remote Sensing
low-illumination remote sensing image enhancement
multi-scale long- and short-range structure aggregation learning
dynamic networks
title Multi-Scale Long- and Short-Range Structure Aggregation Learning for Low-Illumination Remote Sensing Imagery Enhancement
title_full Multi-Scale Long- and Short-Range Structure Aggregation Learning for Low-Illumination Remote Sensing Imagery Enhancement
title_fullStr Multi-Scale Long- and Short-Range Structure Aggregation Learning for Low-Illumination Remote Sensing Imagery Enhancement
title_full_unstemmed Multi-Scale Long- and Short-Range Structure Aggregation Learning for Low-Illumination Remote Sensing Imagery Enhancement
title_short Multi-Scale Long- and Short-Range Structure Aggregation Learning for Low-Illumination Remote Sensing Imagery Enhancement
title_sort multi scale long and short range structure aggregation learning for low illumination remote sensing imagery enhancement
topic low-illumination remote sensing image enhancement
multi-scale long- and short-range structure aggregation learning
dynamic networks
url https://www.mdpi.com/2072-4292/17/2/242
work_keys_str_mv AT yucao multiscalelongandshortrangestructureaggregationlearningforlowilluminationremotesensingimageryenhancement
AT yuyuantian multiscalelongandshortrangestructureaggregationlearningforlowilluminationremotesensingimageryenhancement
AT xiuqinsu multiscalelongandshortrangestructureaggregationlearningforlowilluminationremotesensingimageryenhancement
AT meilinxie multiscalelongandshortrangestructureaggregationlearningforlowilluminationremotesensingimageryenhancement
AT weihao multiscalelongandshortrangestructureaggregationlearningforlowilluminationremotesensingimageryenhancement
AT haitaowang multiscalelongandshortrangestructureaggregationlearningforlowilluminationremotesensingimageryenhancement
AT fanwang multiscalelongandshortrangestructureaggregationlearningforlowilluminationremotesensingimageryenhancement