Fostering Generalization in Single-view 3D Reconstruction by Learning a Hierarchy of Local and Global Shape Priors

被引:9
|
作者
Bechtold, Jan [1 ,2 ]
Tatarchenko, Maxim [1 ]
Fischer, Volker [1 ]
Brox, Thomas [2 ]
机构
[1] Bosch Ctr Artificial Intelligence, Renningen, Baden Wurttembe, Germany
[2] Univ Freiburg, Freiburg, Germany
关键词
D O I
10.1109/CVPR46437.2021.01562
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Single-view 3D object reconstruction has seen much progress, yet methods still struggle generalizing to novel shapes unseen during training. Common approaches predominantly rely on learned global shape priors and, hence, disregard detailed local observations. In this work, we address this issue by learning a hierarchy of priors at different levels of locality from ground truth input depth maps. We argue that exploiting local priors allows our method to efficiently use input observations, thus improving generalization in visible areas of novel shapes. At the same time, the combination of local and global priors enables meaningful hallucination of unobserved parts resulting in consistent 3D shapes. We show that the hierarchical approach generalizes much better than the global approach. It generalizes not only between different instances of a class but also across classes and to unseen arrangements of objects.
引用
收藏
页码:15875 / 15884
页数:10
相关论文
共 50 条
  • [1] Learning Shape Priors for Single-View 3D Completion And Reconstruction
    Wu, Jiajun
    Zhang, Chengkai
    Zhang, Xiuming
    Zhang, Zhoutong
    Freeman, William T.
    Tenenbaum, Joshua B.
    [J]. COMPUTER VISION - ECCV 2018, PT XI, 2018, 11215 : 673 - 691
  • [2] Learning View Priors for Single-view 3D Reconstruction
    Kato, Hiroharu
    Harada, Tatsuya
    [J]. 2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019), 2019, : 9770 - 9779
  • [3] Single-View 3D Object Reconstruction from Shape Priors in Memory
    Yang, Shuo
    Xu, Min
    Xie, Haozhe
    Perry, Stuart
    Xia, Jiahao
    [J]. 2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021, 2021, : 3151 - 3160
  • [4] Single and sparse view 3D reconstruction by learning shape priors
    Chen, Yu
    Cipolla, Roberto
    [J]. COMPUTER VISION AND IMAGE UNDERSTANDING, 2011, 115 (05) : 586 - 602
  • [5] Semi-supervised Single-View 3D Reconstruction via Prototype Shape Priors
    Xing, Zhen
    Li, Hengduo
    Wu, Zuxuan
    Jiang, Yu-Gang
    [J]. COMPUTER VISION - ECCV 2022, PT I, 2022, 13661 : 535 - 551
  • [6] 3D estimation of single-view 2d images using shape priors and transfer learning
    Shoukat, Muhammad Awais
    Sargano, Allah Bux
    You, Lihua
    Habib, Zulfiqar
    [J]. MULTIMEDIA TOOLS AND APPLICATIONS, 2024,
  • [7] 3D estimation of single-view 2d images using shape priors and transfer learning
    Shoukat, Muhammad Awais
    Sargano, Allah Bux
    You, Lihua
    Habib, Zulfiqar
    [J]. MULTIMEDIA TOOLS AND APPLICATIONS, 2024,
  • [8] Single-View 3D Reconstruction of Curves
    Fakih, Ali
    Wilser, Nicola
    Maillot, Yvan
    Cordier, Frederic
    [J]. ADVANCES IN COMPUTER GRAPHICS, CGI 2023, PT II, 2024, 14496 : 3 - 14
  • [9] Single-View 3D reconstruction: A Survey of deep learning methods
    Fahim, George
    Amin, Khalid
    Zarif, Sameh
    [J]. COMPUTERS & GRAPHICS-UK, 2021, 94 : 164 - 190
  • [10] Learning Single-View 3D Reconstruction with Limited Pose Supervision
    Yang, Guandao
    Cui, Yin
    Belongie, Serge
    Hariharan, Bharath
    [J]. COMPUTER VISION - ECCV 2018, PT 15, 2018, 11219 : 90 - 105