AI-Enhanced Remote Sensing for Image Matching and 3D Reconstruction
A special issue of Remote Sensing (ISSN 2072-4292). This special issue belongs to the section "Remote Sensing Image Processing".
Deadline for manuscript submissions: 25 April 2026 | Viewed by 51
Special Issue Editors
Interests: photogrammetry and remote sensing; computer vision; artificial intelligence
Interests: satellite photogrammetry; dense image matching; 3D reconstruction of high-resolution satellites
Special Issues, Collections and Topics in MDPI journals
Interests: 3D reconstruction; deep learning; multimodal large language model
Special Issues, Collections and Topics in MDPI journals
Special Issue Information
Dear Colleagues,
In recent years, research in remote sensing has experienced explosive growth, largely driven by advances in artificial intelligence, particularly in image matching and three-dimensional (3D) reconstruction. This Special Issue, “AI-Enhanced Remote Sensing for Image Matching and 3D Reconstruction”, aims to bring together cutting-edge studies that demonstrate how machine learning and deep learning methods are reshaping the processing, reconstruction, and interpretation of remote sensing imagery.
Key topics covered in this issue include feature detection and matching across diverse sensors (satellite, UAV, LiDAR), dense and sparse image matching, outlier detection, structure-from-motion, depth estimation, and point cloud generation and fusion. These tasks can be significantly enhanced by deep neural networks such as CNNs, Transformers, and even emerging foundation models. In the domain of 3D representation, implicit methods (e.g., NeRF, 3D Gaussian Splatting) have recently emerged as research hotspots. Their main advantage lies in modeling 3D space through continuous functions, thereby overcoming the resolution limitations and topological constraints of traditional explicit representations (such as point clouds and meshes).
Despite these advances, persistent challenges remain, including occlusions, weak or repetitive textures, large-scale scenes, heterogeneous data sources, viewpoint variations, and computational efficiency. This Special Issue highlights innovative algorithmic strategies, data fusion techniques, hybrid modeling approaches, and evaluation frameworks that aim to improve robustness, accuracy, and completeness. Ultimately, it seeks to advance remote sensing toward greater automation, higher fidelity, and broader applicability of 3D spatial information in real-world scenarios. This aligns closely with the journal’s scope. Submissions to this Special Issue may address, but are not limited to, the following topics:
Learning based sensor calibration
Learning based image matching
Foundation model-based feature extraction
Learning based Bunde adjustment
NeRF-based 3D reconstruction
3DGS with remote sensing images
3DGS with linear images
Learning-based 3D reconstruction
Single-view 3D reconstruction
Learning-based orthophoto mosaic/generation
NeRF-based true orthophoto generation
3DGS-based true orthophoto generation
Dr. Maoteng Zheng
Dr. Xu Huang
Dr. Zhi Zheng
Guest Editors
Manuscript Submission Information
Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.
Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Remote Sensing is an international peer-reviewed open access semimonthly journal published by MDPI.
Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2700 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.
Keywords
- learning-based image matching
- learning-based 3D reconstruction
- 3D Gaussian Splatting
- NeRF
- single-view 3D reconstruction
- orthophoto mosaic
Benefits of Publishing in a Special Issue
- Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
- Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
- Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
- External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
- Reprint: MDPI Books provides the opportunity to republish successful Special Issues in book format, both online and in print.
Further information on MDPI's Special Issue policies can be found here.
