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
  • [41] Cascaded Network-Based Single-View Bird 3D Reconstruction
    Su, Pei
    Zhao, Qijun
    Pan, Fan
    Gao, Fei
    ARTIFICIAL NEURAL NETWORKS AND MACHINE LEARNING, ICANN 2023, PT II, 2023, 14255 : 115 - 127
  • [42] Topologically-Aware Deformation Fields for Single-View 3D Reconstruction
    Duggal, Shivam
    Pathak, Deepak
    2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022), 2022, : 1526 - 1536
  • [43] 3D-Mask-GAN:Unsupervised Single-View 3D Object Reconstruction
    Wan, Qun
    Li, Yidong
    Cui, Haidong
    Feng, Zheng
    2019 6TH INTERNATIONAL CONFERENCE ON BEHAVIORAL, ECONOMIC AND SOCIO-CULTURAL COMPUTING (BESC 2019), 2019,
  • [44] Deep Single-View 3D Object Reconstruction with Visual Hull Embedding
    Wang, Hanqing
    Yang, Jiaolong
    Liang, Wei
    Tong, Xin
    THIRTY-THIRD AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTY-FIRST INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE / NINTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2019, : 8941 - 8948
  • [45] What's on the Other Side? A Single-View 3D Scene Reconstruction
    Staszak, Rafal
    Kulecki, Bartlomiej
    Sempruch, Witold
    Belter, Dominik
    2022 17TH INTERNATIONAL CONFERENCE ON CONTROL, AUTOMATION, ROBOTICS AND VISION (ICARCV), 2022, : 173 - 180
  • [46] Single-view 3D object reconstruction based on NFFD and graph convolution
    Lian Y.
    Pei S.
    Hu W.
    Guangxue Jingmi Gongcheng/Optics and Precision Engineering, 2022, 30 (10): : 1189 - 1202
  • [47] Single-view 3D Body and Cloth Reconstruction under Complex Poses
    Ugrinovic, Nicolas
    Pumarola, Albert
    Sanfeliu, Alberto
    Moreno-Noguer, Francesc
    PROCEEDINGS OF THE 17TH INTERNATIONAL JOINT CONFERENCE ON COMPUTER VISION, IMAGING AND COMPUTER GRAPHICS THEORY AND APPLICATIONS (VISAPP), VOL 4, 2022, : 192 - 203
  • [48] Weakly Supervised Part-wise 3D Shape Reconstruction from Single-View RGB Images
    Niu, Chengjie
    Yu, Yang
    Bian, Zhenwei
    Li, Jun
    Xu, Kai
    COMPUTER GRAPHICS FORUM, 2020, 39 (07) : 447 - 457
  • [49] Single-View 3D Face Reconstruction via Cross-View Consistency Constraints
    Zhong Y.
    Pei Y.
    Li P.
    Jisuanji Fuzhu Sheji Yu Tuxingxue Xuebao/Journal of Computer-Aided Design and Computer Graphics, 2024, 36 (04): : 543 - 551
  • [50] Sym3DNet: Symmetric 3D Prior Network for Single-View 3D Reconstruction
    Siddique, Ashraf
    Lee, Seungkyu
    SENSORS, 2022, 22 (02)