The Review of Research on 3D Model Reconstruction Based on Point Cloud Data

Dingnan Shi

doi:10.62051/v6yk2g06

Authors

Dingnan Shi

DOI:

https://doi.org/10.62051/v6yk2g06

Keywords:

3D Model Reconstruction; Point Cloud; Comparison of methods; Classification.

Abstract

Point cloud-based 3D modeling is a cutting-edge technology that leverages point cloud data from sensors like lidar and cameras to recreate detailed 3D models of objects and environments. This paper serves to outline the fundamental route, key principles, and prevalent methods within this field, with a specific emphasis on the preprocessing registration techniques for point cloud data and the advancements in 3D model reconstruction technologies.Furthermore, the article will delve into foundational 3D reconstruction methodologies, categorizing them into optimization-driven approaches and interpolation or fitting strategies. By categorizing these methods, it becomes possible to address the limitations and challenges associated with each algorithm and propose potential enhancement strategies to overcome these obstacles.By refining existing techniques, developing novel methodologies, and enhancing computational efficiency, the future holds promise for significant advancements in the realm of 3D modeling through point cloud data. In the conclusion, we provide a summary and outlook for the entire paper.

Downloads

Download data is not yet available.

References

Z. Zhou et al., "NDT-Transformer: Large-Scale 3D Point Cloud Localisation using the Normal Distribution Transform Representation," 2021 IEEE International Conference on Robotics and Automation (ICRA), Xi'an, China, 2021, pp. 5654-5660. DOI: https://doi.org/10.1109/ICRA48506.2021.9560932

V. Sanchez and A. Zakhor, "Planar 3D modeling of building interiors from point cloud data," 2012 19th IEEE International Conference on Image Processing, Orlando, FL, USA, 2012, pp. 1777-1780.

V. Sanchez and A. Zakhor, "Planar 3D modeling of building interiors from point cloud data," 2012 19th IEEEInternational Conference on Image Processing, Orlando, FL, USA, 2012, pp. 1777-1780. DOI: https://doi.org/10.1109/ICIP.2012.6467225

Sahebdivani, S.; Arefi, H.; Maboudi, M. Rail Track Detection and Projection-Based 3D Modeling from UAV Point Cloud. Sensors 2020, 20, 5220. DOI: https://doi.org/10.3390/s20185220

Salehi, B.; Jarahizadeh, S.; Sarafraz, A. An Improved RANSAC Outlier Rejection Method for UAV-Derived Point Cloud. Remote Sens. 2022, 14, 4917. DOI: https://doi.org/10.3390/rs14194917

Song Junfang, Sun Bin, Pu Yuanyuan, et al. Three-dimensional Reconstruction of Blade Surface Based on Laser Point Cloud Data. Acta Metrologica Sinica, 2023, 44(02):171-177.

Chen K, Zhan K, Yang X C, et al. 3D reconstruction method for laser spiral scanning point cloud, Seventh International Conference on Optical and Photonic Engineering (icOPEN 2019). SPIE, 2019, 11205: 472-477. DOI: https://doi.org/10.1117/12.2541783

Wen Pei, Cheng Yinglei, Yu Wangsheng. A review of deep learning-based point cloud classification methods. Laser & Optoelectronics Progress, 2021, 58(16): 1600003. DOI: https://doi.org/10.3788/LOP202158.1600003

Chen Kun, Liu Xinguo. Light-based global optimal multi-view 3D reconstruction method. Computer Engineering, 2013(11):235-239.

Xu Xinao, LI Yixuan, Qian Jiaming, et al. Real-time high-precision model reconstruction based on global optimisation. Chinese Journal of Liquid Crystal & Displays, 2023, 38(6).