Research on Multi-View 3D Reconstruction Technology Based on SFM

被引:21
|
作者
Gao, Lei [1 ]
Zhao, Yingbao [1 ]
Han, Jingchang [1 ]
Liu, Huixian [1 ]
机构
[1] Hebei Univ Sci & Technol, Sch Elect Engn, Shijiazhuang 050018, Hebei, Peoples R China
关键词
multi-view 3D reconstruction; feature-point detection and matching; sparse reconstruction; a dense reconstruction;
D O I
10.3390/s22124366
中图分类号
O65 [分析化学];
学科分类号
070302 ; 081704 ;
摘要
Multi-view 3D reconstruction technology is used to restore a 3D model of practical value or required objects from a group of images. This paper designs and implements a set of multi-view 3D reconstruction technology, adopts the fusion method of SIFT and SURF feature-point extraction results, increases the number of feature points, adds proportional constraints to improve the robustness of feature-point matching, and uses RANSAC to eliminate false matching. In the sparse reconstruction stage, the traditional incremental SFM algorithm takes a long time, but the accuracy is high; the traditional global SFM algorithm is fast, but its accuracy is low; aiming at the disadvantages of traditional SFM algorithm, this paper proposes a hybrid SFM algorithm, which avoids the problem of the long time consumption of incremental SFM and the problem of the low precision and poor robustness of global SFM; finally, the MVS algorithm of depth-map fusion is used to complete the dense reconstruction of objects, and the related algorithms are used to complete the surface reconstruction, which makes the reconstruction model more realistic.
引用
收藏
页数:17
相关论文
共 50 条
  • [31] 3D Reconstruction from multi-view point cloud Based on particle system
    Hu Wenqiang
    Qu Yi
    2009 IITA INTERNATIONAL CONFERENCE ON CONTROL, AUTOMATION AND SYSTEMS ENGINEERING, PROCEEDINGS, 2009, : 500 - +
  • [32] Multi-view 3D Reconstruction Based on Deformable Convolution and Laplace Pyramid Residuals
    Hao, Zhaoming
    Zhang, Ziyang
    Li, Hongyan
    Xu, Baoqing
    Zhang, Xiaoqiong
    Xu, Meng
    Wang, Weifeng
    IAENG International Journal of Computer Science, 2024, 51 (07) : 896 - 905
  • [33] Multi-view 3D reconstruction based on deep learning: A survey and comparison of methods
    Wu, Juhao
    Wyman, Omar
    Tang, Yadong
    Pasini, Damiano
    Wang, Wenlong
    Neurocomputing, 2024, 582
  • [34] Multi-Head Attention Refiner for Multi-View 3D Reconstruction
    Lee, Kyunghee
    Cho, Ihjoon
    Yang, Boseung
    Park, Unsang
    JOURNAL OF IMAGING, 2024, 10 (11)
  • [35] Multi-View Image-Based 3D Reconstruction in Indoor Scenes:A Survey
    LU Ping
    SHI Wenzhe
    QIAO Xiuquan
    ZTE Communications, 2024, 22 (03) : 91 - 98
  • [36] A Hybrid Multi-View 3D Reconstruction Method Based on Scene Graph Partition
    Xue J.-S.
    Yi H.
    Wu Z.-H.
    Chen X.-N.
    Zidonghua Xuebao/Acta Automatica Sinica, 2020, 46 (04): : 782 - 795
  • [37] Fast Multi-View 3D reconstruction of seedlings based on automatic viewpoint planning
    Wei, Kaihua
    Liu, Shuang
    Chen, Qingguang
    Huang, Shentao
    Zhong, Mingwei
    Zhang, Jingcheng
    Sun, Hongwei
    Wu, Kaihua
    Fan, Shanhui
    Ye, Ziran
    Kong, Dedong
    COMPUTERS AND ELECTRONICS IN AGRICULTURE, 2024, 218
  • [38] TMVNet : Using Transformers for Multi-view Voxel-based 3D Reconstruction
    Peng, Kebin
    Islam, Rifatul
    Quarles, John
    Desai, Kevin
    2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS, CVPRW 2022, 2022, : 221 - 229
  • [39] Multi-view 3D reconstruction based on deep learning: A survey and comparison of methods
    Wu, Juhao
    Wyman, Omar
    Tang, Yadong
    Pasini, Damiano
    Wang, Wenlong
    NEUROCOMPUTING, 2024, 582
  • [40] Multi-View 3D Reconstruction Method Based on Self-Attention Mechanism
    Zhu, Guangzhao
    Bo, Wei
    Yang, Afeng
    Xin, Xu
    LASER & OPTOELECTRONICS PROGRESS, 2023, 60 (16)