A Multi-Path Feature Extraction and Transformer Feature Enhancement DEM Super-Resolution Reconstruction Network

In recent years, great progress has been made in the field of super-resolution (SR) reconstruction based on deep learning techniques. Although image SR techniques show strong potential in image reconstruction, the effective application of these techniques to SR reconstruction of digital elevation mo...

Full description

Saved in:
Bibliographic Details
Main Authors: Mingqiang Guo, Feng Xiong, Ying Huang, Zhizheng Zhang, Jiaming Zhang
Format: Article
Language:English
Published: MDPI AG 2025-05-01
Series:Remote Sensing
Subjects:
Online Access:https://www.mdpi.com/2072-4292/17/10/1737
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849719742083891200
author Mingqiang Guo
Feng Xiong
Ying Huang
Zhizheng Zhang
Jiaming Zhang
author_facet Mingqiang Guo
Feng Xiong
Ying Huang
Zhizheng Zhang
Jiaming Zhang
author_sort Mingqiang Guo
collection DOAJ
description In recent years, great progress has been made in the field of super-resolution (SR) reconstruction based on deep learning techniques. Although image SR techniques show strong potential in image reconstruction, the effective application of these techniques to SR reconstruction of digital elevation models (DEMs) remains an important research challenge. The complexity and diversity of DEMs limits existing methods to capture subtle changes and features of the terrain, thus affecting the quality of reconstruction. To solve this problem, a DEM SR reconstruction network based on multi-path feature extraction and transformer feature enhancement is proposed in this paper. The network structure has three parts: feature extraction, image reconstruction, and feature enhancement. The feature extraction component consists of three feature extraction blocks, and each feature extraction block contains multiple multi-path feature residuals to enhance the interaction between spatial information and semantic information, so as to fully extract image features. In addition, the transformer feature enhancement module uses an encoder and decoder based design, leveraging the correlation between low- and high-dimensional features to further improve network performance. Through repeated testing and improvement, the model shows excellent performance in high-resolution DEM image reconstruction, and can generate more accurate DEMs. In terms of elevation and slope evaluation indexes, the model was 3.41% and 1.11% better compared with the existing reconstruction methods, which promotes the application of SR reconstruction technology in terrain data.
format Article
id doaj-art-17b47e4399a9477494783e2df1e1247d
institution DOAJ
issn 2072-4292
language English
publishDate 2025-05-01
publisher MDPI AG
record_format Article
series Remote Sensing
spelling doaj-art-17b47e4399a9477494783e2df1e1247d2025-08-20T03:12:05ZengMDPI AGRemote Sensing2072-42922025-05-011710173710.3390/rs17101737A Multi-Path Feature Extraction and Transformer Feature Enhancement DEM Super-Resolution Reconstruction NetworkMingqiang Guo0Feng Xiong1Ying Huang2Zhizheng Zhang3Jiaming Zhang4School of Computer Science, China University of Geosciences, Wuhan 430074, ChinaSchool of Computer Science, China University of Geosciences, Wuhan 430074, ChinaWuhan Zondy Cyber Technology Co., Ltd., Wuhan 430074, ChinaState Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan 430074, ChinaCollege of Engineering, Boston University, Boston, MA 02215, USAIn recent years, great progress has been made in the field of super-resolution (SR) reconstruction based on deep learning techniques. Although image SR techniques show strong potential in image reconstruction, the effective application of these techniques to SR reconstruction of digital elevation models (DEMs) remains an important research challenge. The complexity and diversity of DEMs limits existing methods to capture subtle changes and features of the terrain, thus affecting the quality of reconstruction. To solve this problem, a DEM SR reconstruction network based on multi-path feature extraction and transformer feature enhancement is proposed in this paper. The network structure has three parts: feature extraction, image reconstruction, and feature enhancement. The feature extraction component consists of three feature extraction blocks, and each feature extraction block contains multiple multi-path feature residuals to enhance the interaction between spatial information and semantic information, so as to fully extract image features. In addition, the transformer feature enhancement module uses an encoder and decoder based design, leveraging the correlation between low- and high-dimensional features to further improve network performance. Through repeated testing and improvement, the model shows excellent performance in high-resolution DEM image reconstruction, and can generate more accurate DEMs. In terms of elevation and slope evaluation indexes, the model was 3.41% and 1.11% better compared with the existing reconstruction methods, which promotes the application of SR reconstruction technology in terrain data.https://www.mdpi.com/2072-4292/17/10/1737digital elevation modelsuper-resolution reconstructionmulti-path feature extractiontransformer feature enhancement
spellingShingle Mingqiang Guo
Feng Xiong
Ying Huang
Zhizheng Zhang
Jiaming Zhang
A Multi-Path Feature Extraction and Transformer Feature Enhancement DEM Super-Resolution Reconstruction Network
Remote Sensing
digital elevation model
super-resolution reconstruction
multi-path feature extraction
transformer feature enhancement
title A Multi-Path Feature Extraction and Transformer Feature Enhancement DEM Super-Resolution Reconstruction Network
title_full A Multi-Path Feature Extraction and Transformer Feature Enhancement DEM Super-Resolution Reconstruction Network
title_fullStr A Multi-Path Feature Extraction and Transformer Feature Enhancement DEM Super-Resolution Reconstruction Network
title_full_unstemmed A Multi-Path Feature Extraction and Transformer Feature Enhancement DEM Super-Resolution Reconstruction Network
title_short A Multi-Path Feature Extraction and Transformer Feature Enhancement DEM Super-Resolution Reconstruction Network
title_sort multi path feature extraction and transformer feature enhancement dem super resolution reconstruction network
topic digital elevation model
super-resolution reconstruction
multi-path feature extraction
transformer feature enhancement
url https://www.mdpi.com/2072-4292/17/10/1737
work_keys_str_mv AT mingqiangguo amultipathfeatureextractionandtransformerfeatureenhancementdemsuperresolutionreconstructionnetwork
AT fengxiong amultipathfeatureextractionandtransformerfeatureenhancementdemsuperresolutionreconstructionnetwork
AT yinghuang amultipathfeatureextractionandtransformerfeatureenhancementdemsuperresolutionreconstructionnetwork
AT zhizhengzhang amultipathfeatureextractionandtransformerfeatureenhancementdemsuperresolutionreconstructionnetwork
AT jiamingzhang amultipathfeatureextractionandtransformerfeatureenhancementdemsuperresolutionreconstructionnetwork
AT mingqiangguo multipathfeatureextractionandtransformerfeatureenhancementdemsuperresolutionreconstructionnetwork
AT fengxiong multipathfeatureextractionandtransformerfeatureenhancementdemsuperresolutionreconstructionnetwork
AT yinghuang multipathfeatureextractionandtransformerfeatureenhancementdemsuperresolutionreconstructionnetwork
AT zhizhengzhang multipathfeatureextractionandtransformerfeatureenhancementdemsuperresolutionreconstructionnetwork
AT jiamingzhang multipathfeatureextractionandtransformerfeatureenhancementdemsuperresolutionreconstructionnetwork