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

被引:13
|
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
  • [31] 3D Priors for Scene Learning from a Single View
    Rother, Diego
    Patwardban, Kedar
    Aganj, Iman
    Sapiro, Guillermo
    2008 IEEE COMPUTER SOCIETY CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS, VOLS 1-3, 2008, : 635 - +
  • [32] FaceScape: 3D Facial Dataset and Benchmark for Single-View 3D Face Reconstruction
    Zhu, Hao
    Yang, Haotian
    Guo, Longwei
    Zhang, Yidi
    Wang, Yanru
    Huang, Mingkai
    Wu, Menghua
    Shen, Qiu
    Yang, Ruigang
    Cao, Xun
    IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2023, 45 (12) : 14528 - 14545
  • [33] What Do Single-view 3D Reconstruction Networks Learn?
    Tatarchenko, Maxim
    Richter, Stephan R.
    Ranftl, Rene
    Li, Zhuwen
    Koltun, Vladlen
    Brox, Thomas
    2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019), 2019, : 3400 - 3409
  • [34] 2D GANs Meet Unsupervised Single-View 3D Reconstruction
    Liu, Feng
    Liu, Xiaoming
    COMPUTER VISION - ECCV 2022, PT I, 2022, 13661 : 497 - 514
  • [35] 3D Reconstruction and Estimation from Single-view 2D Image by Deep Learning A Survey
    Shan, Yongfeng
    Liang, Christy Jie
    Xu, Min
    2024 IEEE CONFERENCE ON ARTIFICIAL INTELLIGENCE, CAI 2024, 2024, : 1 - 7
  • [36] Self-supervised reflectance-guided 3d shape reconstruction from single-view images
    Fang, Binbin
    Xiao, Nanfeng
    APPLIED INTELLIGENCE, 2023, 53 (06) : 6966 - 6977
  • [37] Generalizing Single-View 3D Shape Retrieval to Occlusions and Unseen Objects
    Wu, Qirui
    Ritchie, Daniel
    Savva, Manolis
    Chang, Angel X.
    2024 INTERNATIONAL CONFERENCE IN 3D VISION, 3DV 2024, 2024, : 893 - 902
  • [38] Toward Realistic Single-View 3D Object Reconstruction with Unsupervised Learning from Multiple Images
    Long-Nhat Ho
    Anh Tuan Tran
    Quynh Phung
    Minh Hoai
    2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021), 2021, : 12580 - 12590
  • [39] Self-supervised reflectance-guided 3d shape reconstruction from single-view images
    Binbin Fang
    Nanfeng Xiao
    Applied Intelligence, 2023, 53 : 6966 - 6977
  • [40] Single-View 3D Garment Reconstruction Using Neural Volumetric Rendering
    Chen, Yizheng
    Xie, Rengan
    Yang, Sen
    Dai, Linchen
    Sun, Hongchun
    Huo, Yuchi
    Li, Rong
    IEEE ACCESS, 2024, 12 : 49682 - 49693