Implicit Function-based 3D Reconstruction for Point Cloud Data
Article Sidebar
Main Article Content
Abstract
3D reconstruction from point cloud data has become a key component in various domains such as computer graphics, medical imaging, industrial design, and virtual reality. Among the many available approaches, implicit function methods have attracted significant attention due to their robustness and their ability to generate high-quality surface meshes from sparse and noisy data. This paper investigates the fundamental principles of 3D reconstruction, with a particular focus on the application of space-partitioned local fitting methods in implicit surface reconstruction from point clouds. Furthermore, we introduce a hybrid normal estimation and orientation technique to enhance global surface consistency. Experimental results on LiDAR point clouds demonstrate the accuracy and efficiency of the proposed reconstruction pipeline, validating its effectiveness.
Downloads
Article Details
Copyright (c) 2025 Li Y, et al.
This work is licensed under a Creative Commons Attribution 4.0 International License.
Huang X, Mei G, Zhang J, Abbas R. A comprehensive survey on point cloud registration. arXiv [Preprint]. 2021; arXiv:2103.02690. Available from: https://doi.org/10.48550/arXiv.2103.02690
Zhang T, Yuan H, Qi L, Zhang J, Zhou Q, Ji S. Point cloud Mamba: Point cloud learning via state space model. In: Proceedings of the AAAI Conference on Artificial Intelligence. 2025;39:10121–10130. Available from: https://doi.org/10.1609/aaai.v39i10.33098
Chibane J, Alldieck T, Pons-Moll G. Implicit functions in feature space for 3D shape reconstruction and completion. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2020;6970–6981. Available from: https://doi.org/10.1109/CVPR42600.2020.00700
Choy CB, Xu D, Gwak J, Chen K, Savarese S. 3D-R2N2: A unified approach for single and multi-view 3D object reconstruction. In: Computer Vision – ECCV 2016: 14th European Conference on Computer Vision; 2016 Nov 11–14; Amsterdam, The Netherlands. Proceedings, Part VIII. Springer; 2016;628–644. Available from: https://arxiv.org/abs/1604.00449
Carr JC, Beatson RK, Cherrie JB, Mitchell TJ, Fright WR, McCallum BC, et al. Reconstruction and representation of 3D objects with radial basis functions. In: Proceedings of the 28th Annual Conference on Computer Graphics and Interactive Techniques (SIGGRAPH). 2001; p. 67–76. Available from: https://doi.org/10.1145/383259.383266
Nguyen TT, Nguyen QM, Liu XG, Ziggah YY. 3D object model reconstruction based on laser scanning point cloud data. In: International Symposium on Geoinformatics for Spatial Infrastructure Development in Earth and Allied Sciences. 2012. Available from: https://www.researchgate.net/publication/306278163_3D_OBJECT_MODEL_RECONSTRUCTION_BASED_ON_LASER_SC…
Li X, Wang Y, Liu Y, Gao X, Song B. Qiyun Pagoda 3D model reconstruction based on laser cloud data. Surv Mapp. 2011;9:11–14.
Boulch A. ConvPoint: Continuous convolutions for point cloud processing. Comput Graph. 2020;88:24–34. Available from: https://doi.org/10.48550/arXiv.1904.02375
Brunetaud X, De Luca L, Janvier-Badosa S, Beck K, Al-Mukhtar M. Application of digital techniques in monument preservation. Eur J Environ Civ Eng. 2012;16(5):543–556. Available from: https://doi.org/10.1080/19648189.2012.676365
Kwak E, Detchev I, Habib A, El-Badry M, Hughes C. Precise photogrammetric reconstruction using model-based image fitting for 3D beam deformation monitoring. J Surv Eng. 2013;139(3):143–155. Available from: https://doi.org/10.1061/(ASCE)SU.1943-5428.0000105
Ren P, Wang W, Bai X. Reconstruction of Imperial University of Shanxi based on virtual reality technology. Comput Simul. 2012;29(11):20–23.
Wang P, Wang Z, Xin S, Gao X, Wang W, Tu C. Restricted Delaunay triangulation for explicit surface reconstruction. ACM Trans Graph. 2022;41(5):1–20. Available from: https://doi.org/10.1145/3533768
Lei H. OffsetOPT: Explicit surface reconstruction without normals. arXiv [Preprint]. 2025; arXiv:2503.15763. Available from: https://doi.org/10.48550/arXiv.2503.15763
Berger M, Tagliasacchi A, Seversky LM, Alliez P, Guennebaud G, Levine JA, et al. A survey of surface reconstruction from point clouds. Comput Graph Forum. 2017;36(1):301–329. Available from: https://doi.org/10.1111/cgf.12802
Ham H, Wesley J, Hendra H. Computer vision-based 3D reconstruction: A review. Int J Electr Comput Eng. 2019;9(4):2394–2402. Available from: https://doi.org/10.11591/ijece.v9i4.pp2394-2402
Huang Z, Wen Y, Wang Z, Ren J, Jia K. Surface reconstruction from point clouds: A survey and a benchmark. IEEE Trans Pattern Anal Mach Intell. 2024. Available from: https://doi.org/10.1109/tpami.2024.3429209
Lim SP, Haron H. Surface reconstruction techniques: A review. Artif Intell Rev. 2014;42(1):59–78. Available from: https://link.springer.com/article/10.1007/s10462-012-9329-z
Zhao HK, Osher S, Fedkiw R. Fast surface reconstruction using the level set method. In: Proceedings of the IEEE Workshop on Variational and Level Set Methods in Computer Vision. 2001; p. 194–201. Available from: https://doi.org/10.1109/VLSM.2001.938900
Kazhdan M, Hoppe H. Screened Poisson surface reconstruction. ACM Trans Graph. 2013;32(3):1–13. Available from: https://doi.org/10.1145/2487228.2487237
Liu P, Zeng Z, Wang Q, Chen M, Zhang G. Geometry-enhanced implicit function for detailed clothed human reconstruction with RGB-D. arXiv [Preprint]. 2025; arXiv:2503.17921. Available from: https://doi.org/10.1049/cit2.70009