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
  • [21] Perspective Transformer Nets: Learning Single-View 3D Object Reconstruction without 3D Supervision
    Yan, Xinchen
    Yang, Jimei
    Yumer, Ersin
    Guo, Yijie
    Lee, Honglak
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 29 (NIPS 2016), 2016, 29
  • [22] Single-view 3D Reconstruction Algorithm Based on View-aware
    Wang Nian
    Hu Xuyang
    Zhu Fan
    Tang Jun
    JOURNAL OF ELECTRONICS & INFORMATION TECHNOLOGY, 2020, 42 (12) : 3053 - 3060
  • [23] Single-View 3D Mesh Reconstruction for Seen and Unseen Categories
    Yang, Xianghui
    Lin, Guosheng
    Zhou, Luping
    IEEE TRANSACTIONS ON IMAGE PROCESSING, 2023, 32 : 3746 - 3758
  • [24] Visual enhancement of single-view 3D point cloud reconstruction
    Ping, Guiju
    Esfahani, Mahdi Abolfazli
    Chen, Jiaying
    Wang, Han
    COMPUTERS & GRAPHICS-UK, 2022, 102 : 112 - 119
  • [25] Deep Learning-Based Single-View Fluorescence Dose Reconstruction for 3D Dosimetry
    Nomura, Y.
    Ashraf, M. R.
    Xing, L.
    INTERNATIONAL JOURNAL OF RADIATION ONCOLOGY BIOLOGY PHYSICS, 2023, 117 (02): : S49 - S50
  • [26] Viewpoint-independent Single-view 3D Object Reconstruction using Reinforcement Learning
    Ito, Seiya
    Ju, Byeongjun
    Kaneko, Naoshi
    Sumi, Kazuhiko
    PROCEEDINGS OF THE 17TH INTERNATIONAL JOINT CONFERENCE ON COMPUTER VISION, IMAGING AND COMPUTER GRAPHICS THEORY AND APPLICATIONS (VISAPP), VOL 5, 2022, : 811 - 819
  • [27] Learning pose-invariant 3D object reconstruction from single-view images
    Peng, Bo
    Wang, Wei
    Dong, Jing
    Tan, Tieniu
    NEUROCOMPUTING, 2021, 423 : 407 - 418
  • [28] 3D Reconstruction of Gastrointestinal Regions Using Single-View Methods
    Ahmad, Bilal
    Floor, Pal Anders
    Farup, Ivar
    Hovde, Oistein
    IEEE ACCESS, 2023, 11 : 61103 - 61117
  • [29] Single-View 3D Scene Reconstruction and Parsing by Attribute Grammar
    Liu, Xiaobai
    Zhao, Yibiao
    Zhu, Song-Chun
    IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2018, 40 (03) : 710 - 725
  • [30] 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 - +