Accurate 3D Shape Reconstruction from Single Structured-Light Image via Fringe-to-Fringe Network

被引:23
作者
Nguyen, Hieu [1 ,2 ]
Wang, Zhaoyang [1 ]
机构
[1] Catholic Univ Amer, Dept Mech Engn, Washington, DC 20064 USA
[2] NIDA, Neuroimaging Res Branch, NIH, Baltimore, MD 21224 USA
基金
美国国家卫生研究院;
关键词
three-dimensional sensing; three-dimensional shape reconstruction; single-shot imaging; height measurements; depth measurements; deep learning; convolutional neural networks; PHASE RETRIEVAL; REAL-TIME; DEEP; PROJECTION; PROFILOMETRY; METROLOGY; PATTERN; NET;
D O I
10.3390/photonics8110459
中图分类号
O43 [光学];
学科分类号
070207 ; 0803 ;
摘要
Accurate three-dimensional (3D) shape reconstruction of objects from a single image is a challenging task, yet it is highly demanded by numerous applications. This paper presents a novel 3D shape reconstruction technique integrating a high-accuracy structured-light method with a deep neural network learning scheme. The proposed approach employs a convolutional neural network (CNN) to transform a color structured-light fringe image into multiple triple-frequency phase-shifted grayscale fringe images, from which the 3D shape can be accurately reconstructed. The robustness of the proposed technique is verified, and it can be a promising 3D imaging tool in future scientific and industrial applications.
引用
收藏
页数:14
相关论文
共 50 条
  • [41] Time-overlapping structured-light projection: high performance on 3D shape measurement for complex dynamic scenes
    Wu, Zhoujie
    Guo, Wenbo
    Zhang, Qican
    Wang, Haoran
    Li, Xunren
    Chen, Zhengdong
    [J]. OPTICS EXPRESS, 2022, 30 (13) : 22467 - 22486
  • [42] High-quality 3D shape measurement using saturated fringe patterns
    Chen, Bo
    Zhang, Song
    [J]. OPTICS AND LASERS IN ENGINEERING, 2016, 87 : 83 - 89
  • [43] Comparison of 3D sensing algorithms for single shot fringe projection profilometry
    Dhanotia, Jitendra
    Chatterjee, Amit
    Bhatia, Vimal
    Prakash, Shashi
    [J]. 2018 3RD INTERNATIONAL CONFERENCE ON MICROWAVE AND PHOTONICS (ICMAP), 2018,
  • [44] RealPoint3D: An Efficient Generation Network for 3D Object Reconstruction From a Single Image
    Zhang, Yang
    Liu, Zhen
    Liu, Tianpeng
    Peng, Bo
    Li, Xiang
    [J]. IEEE ACCESS, 2019, 7 : 57539 - 57549
  • [45] 3D shape from phase errors by using binary fringe with multi-step phase-shift technique
    Liu, Yuankun
    Zhang, Qican
    Su, Xianyu
    [J]. OPTICS AND LASERS IN ENGINEERING, 2015, 74 : 22 - 27
  • [46] Single-shot 3D measurement via deep learning fringe projection profilometry with geometric constraints
    Li, Ze
    Wang, Jianhua
    Wang, Suzhen
    Zhang, Wen
    Shan, Shuo
    Yang, Yanxi
    [J]. OPTICS AND LASER TECHNOLOGY, 2025, 181
  • [47] PushNet: 3D reconstruction from a single image by pushing
    Ping, Guiju
    Wang, Han
    [J]. NEURAL COMPUTING & APPLICATIONS, 2024, 36 (12) : 6629 - 6641
  • [48] PushNet: 3D reconstruction from a single image by pushing
    Guiju Ping
    Han Wang
    [J]. Neural Computing and Applications, 2024, 36 : 6629 - 6641
  • [49] Learning-based absolute 3D shape measurement based on single fringe phase retrieval and speckle correlation
    Yin, Wei
    Zuo, Chao
    Feng, Shijie
    Tao, Tianyang
    Chen, Qian
    [J]. OPTICS FRONTIER ONLINE 2020: OPTICS IMAGING AND DISPLAY, 2020, 11571
  • [50] Different structured-light patterns in single-shot 2D-to-3D image conversion using deep learning
    Nguyen, Andrew-Hieu
    Sun, Brian
    LI, Charlotte Qiong
    Wang, Zhaoyang
    [J]. APPLIED OPTICS, 2022, 61 (34) : 10105 - 10115