New Insight into Point Cloud Data Processing

Dear Colleagues,

In recent years, the study of neural networks in three-dimensional space has received widespread attention from many researchers. Subsequently, neural networks also bring new challenges to 3D point cloud data processing. Compared to traditional methods, neural networks necessitate the utilization of multimodal data to construct enriched 3D point cloud datasets. Simultaneously, the difficulty in annotating 3D data calls for innovative approaches employing 2D information to supervise 3D network training or guide 3D information annotation. Moreover, 3D point cloud data processing, such as noise reduction, precise densification, registration, and uniformization, is crucial to optimize point cloud data for subsequent applications, including recognition, segmentation, semantic understanding, the construction of geometric models, etc. This Special Issue seeks to establish a collaborative platform for researchers to delve into and propose effective solutions for the following critical aspects: (1) strategies for leveraging multimodal data to build comprehensive 3D point cloud datasets to facilitate the robust analysis and training of 3D models; (2) novel methodologies leveraging 2D information to supervise the training of 3D networks or guide the annotation of 3D information; and (3) innovative techniques to preprocess 3D point cloud data to optimize the quality and uniformity of point cloud data.

Submissions exploring, but not limited to, the following topics are welcome:

• Multimodal data integration for comprehensive 3D point cloud dataset construction;
• Novel approaches for guiding 3D network training through 2D supervision;
• Employing 2D information to guide 3D information annotation;
• Advanced techniques of preprocessing 3D point cloud data for optimal downstream applications, including noise cleaning, precise densification, registration, uniformization, etc.

Prof. Dr. Jun Xiao
Dr. Lupeng Liu
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 point cloud
• deep learning
• three-dimensional dataset construction
• three-dimensional information annotation
• noise cleaning
• precise densification
• registration
• uniformization