Advances in 3D Reconstruction Based on Remote Sensing Imagery and Lidar Point Cloud

Dear Colleagues,

As a fundamental problem in remote sensing, 3D reconstruction has continued to attract the attention of researchers over recent decades. The ability to create detailed digital replicas of physical spaces is essential for various applications, ranging from urban planning, building construction, and forest management to virtual tourism. This has led to an increased demand for sophisticated 3D reconstruction techniques that can capture the intricacies of built and natural environments.

Over the past few years, the methodologies for 3D reconstruction have advanced rapidly, with significant strides in data acquisition, deep learning algorithms, and large-scale model development. In terms of data, satellite and UAV imagery continue to grow while laser scanning equipment becomes increasingly affordable and widely available, and simulated point cloud data are gradually increasing. The integration of multi-modal data sources, such as satellite imagery, aerial photography, and point cloud, has enabled the creation of more comprehensive and accurate 3D models. Implicit 3D reconstruction methods (e.g., neural radiance fields, NeRF) and 3D Gaussian splatting (3DGS) have shown great potential in creating high-quality reconstructions from sparse input views. Furthermore, the advent of large models has revolutionized the field, with models capable of cross-modal learning and depth recovery, leading to more robust and automated reconstruction processes.

As a forum for recent advances and developments in the research and applications of 3D reconstruction from remote sensing imagery and LiDAR point cloud, especially with a focus on deep learning algorithms, this issue calls for the latest findings and innovative work conducted on understanding and modeling natural and artificial scenes, including related data generation and fusion or annotation methods. Submissions can cover one or more of the following themes:

• Advances in 3D reconstruction algorithms and techniques;
• The integration of multi-modal data sources for enhanced 3D modeling;
• Three-dimensional reconstruction of architecture, cultural heritage, and natural scenes;
• Three-dimensional reconstruction of disaster management and emergency response;
• Real-scene 3D reconstruction for geological, topographical, and urban analysis;
• Contributions of 3D reconstruction to a low-altitude economy.

Dr. Fuxun Liang
Dr. Shuang Song
Dr. Bing Wang
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.

• three-dimensional reconstruction
• remote sensing image
• LiDAR point cloud
• multi-modality fusion
• semantic segmentation
• deep learning
• neural radiation field (NeRF)
• 3D Gaussian splatting (3DGS)
• generative modeling
• large models
• ubiquitous point cloud interpretation
• 3D scene modeling
• building reconstruction
• indoor modeling
• natural scene reconstruction
• digital twins