Local frequency interpretation and non-local self-similarity on graph for point cloud inpainting

W Hu, Z Fu, Z Guo - IEEE Transactions on Image Processing, 2019 - ieeexplore.ieee.org
As 3D scanning devices and depth sensors mature, point clouds have attracted increasing
attention as a format for 3D object representation, with applications in various fields such as …

A survey on algorithms of hole filling in 3D surface reconstruction

X Guo, J Xiao, Y Wang - The Visual Computer, 2018 - Springer
The surface reconstruction of 3D objects has attracted more and more attention for its
widespread application in many areas, such as computer science, cultural heritage …

Dynamic point cloud inpainting via spatial-temporal graph learning

Z Fu, W Hu - IEEE Transactions on Multimedia, 2021 - ieeexplore.ieee.org
The maturity of depth sensors and laser scanning techniques has enabled the convenient
acquisition of 3D dynamic point clouds—one natural representation of 3D objects/scenes in …

Point cloud generation for critical transportation infrastructure through Bézier curve

Q Hou, C Ai - Automation in Construction, 2024 - Elsevier
Abstract While Light Detection and Ranging (LiDAR)-based sensors exhibit considerable
potential for transportation infrastructure management, not all infrastructure elements can be …

Point cloud inpainting on graphs from non-local self-similarity

Z Fu, W Hu, Z Guo - 2018 25th IEEE International Conference …, 2018 - ieeexplore.ieee.org
As 3D scanning devices and depth sensors advance, point clouds have attracted increasing
attention as a format for 3D object representation, with applications in various fields such as …

Incomplete region estimation and restoration of 3d point cloud human face datasets

K Uddin, TH Jeong, BT Oh - Sensors, 2022 - mdpi.com
Owing to imperfect scans, occlusions, low reflectance of the scanned surface, and packet
loss, there may be several incomplete regions in the 3D point cloud dataset. These missing …

Point cloud occlusion recovery with shallow feedforward neural networks

L Barazzetti - Advanced Engineering Informatics, 2018 - Elsevier
Abstract 3D scenes reconstructed from point clouds, acquired by either laser scanning or
photogrammetry, are subject to data voids generated by occluding objects. Modeling from …

3D dynamic point cloud inpainting via temporal consistency on graphs

Z Fu, W Hu, Z Guo - 2020 IEEE International Conference on …, 2020 - ieeexplore.ieee.org
With the development of 3D laser scanning techniques and depth sensors, 3D dynamic
point clouds have attracted increasing attention as a representation of 3D objects in motion …

Holes filling of scattered point cloud based on simplification

H Chen, W Cui - Multimedia Tools and Applications, 2022 - Springer
To address the problem of feature points missing and surface holes after 3D reconstruction.
A method of filling holes after extracting feature points of point cloud data is proposed. In this …

Hole filling in 3D scans for digital anthropometric applications

S Sobhiyeh, M Dechenaud, A Dunkel… - 2019 41st Annual …, 2019 - ieeexplore.ieee.org
Anthropometric measurements have been used to assess an individual's body composition,
disease risk, and nutritional status. Three-dimensional (3D) optical devices can rapidly …