Complex 3D General Object Reconstruction from Line Drawings

被引:12
|
作者
Yang, Linjie [1 ]
Liu, Jianzhuang [1 ,2 ,3 ]
Tang, Xiaoou [1 ,2 ]
机构
[1] Chinese Univ Hong Kong, Dept Informat Engn, Hong Kong, Hong Kong, Peoples R China
[2] Chinese Acad Sci, Shenzhen Inst Adv Technol, Shenzhen Key Lab Comp Vis & Pattern Recognit, Beijing 100864, Peoples R China
[3] Huawei Technol Co Ltd, Media Lab, Wuhan, Peoples R China
关键词
MANIFOLD OBJECT; OPTIMIZATION; SHAPE; MODELS; FACES;
D O I
10.1109/ICCV.2013.181
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
An important topic in computer vision is 3D object reconstruction from line drawings. Previous algorithms either deal with simple general objects or are limited to only manifolds (a subset of solids). In this paper, we propose a novel approach to 3D reconstruction of complex general objects, including manifolds, non-manifold solids, and non-solids. Through developing some 3D object properties, we use the degree of freedom of objects to decompose a complex line drawing into multiple simpler line drawings that represent meaningful building blocks of a complex object. After 3D objects are reconstructed from the decomposed line drawings, they are merged to form a complex object from their touching faces, edges, and vertices. Our experiments show a number of reconstruction examples from both complex line drawings and images with line drawings superimposed. Comparisons are also given to indicate that our algorithm can deal with much more complex line drawings of general objects than previous algorithms.
引用
收藏
页码:1433 / 1440
页数:8
相关论文
共 50 条
  • [41] 3D object reconstruction from aerial stereo images
    Zlatanova, S
    Paintsil, J
    Tempfli, K
    WSCG '98, VOL 3: SIXTH INTERNATIONAL CONFERENCE IN CENTRAL EUROPE ON COMPUTER GRAPHICS AND VISUALIZATION 98, 1998, : 472 - 478
  • [42] 3D object reconstruction from engineering drawing projections
    Institute of Engineering Cybernetics, National Academy of Sciences, Surganova 6, 220012 Minsk, Belarus
    Comput Control Eng J, 6 (277-284):
  • [43] Reconstruction of 3D configuration of object from infrared images
    Fan, Y
    Wang, DZ
    VISUAL INFORMATION PROCESSING V, 1996, 2753 : 134 - 138
  • [44] 3D object reconstruction from engineering drawing projections
    Ablameyko, S
    Bereishik, V
    Gorelik, A
    Medvedev, S
    COMPUTING & CONTROL ENGINEERING JOURNAL, 1999, 10 (06): : 277 - 284
  • [45] Reconstruction of 3D Object Meshes from Silhouette Images
    Anselmo Antunes Montenegro
    Luiz Velho
    Paulo C. P. Carvalho
    Jonas Sossai
    Journal of Mathematical Imaging and Vision, 2007, 29 : 119 - 130
  • [46] From Points to Multi-Object 3D Reconstruction
    Engelmann, Francis
    Rematas, Konstantinos
    Leibe, Bastian
    Ferrari, Vittorio
    2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021, 2021, : 4586 - 4595
  • [47] Toward 3D object reconstruction from stereo images
    Xie, Haozhe
    Yao, Hongxun
    Zhou, Shangchen
    Zhang, Shengping
    Tong, Xiaojun
    Sun, Wenxiu
    Neurocomputing, 2021, 463 : 444 - 453
  • [48] Toward 3D object reconstruction from stereo images
    Xie, Haozhe
    Yao, Hongxun
    Zhou, Shangchen
    Zhang, Shengping
    Tong, Xiaojun
    Sun, Wenxiu
    NEUROCOMPUTING, 2021, 463 : 444 - 453
  • [49] Reconstruction of 3D object meshes from silhouette images
    Montenegro, Anselmo Antunes
    Velho, Luiz
    Carvalho, Paulo C. P.
    Sossai, Jonas, Jr.
    JOURNAL OF MATHEMATICAL IMAGING AND VISION, 2007, 29 (2-3) : 119 - 130
  • [50] TRUE 3-D OBJECT RECONSTRUCTION FROM LINE INTEGRALS
    LEVITAN, E
    PROCEEDINGS OF THE IEEE, 1979, 67 (12) : 1679 - 1680