Large Scale Novel Object Discovery in 3D

被引:3
|
作者
Srivastava, Siddharth [1 ]
Sharma, Gaurav [2 ]
Lall, Brejesh [1 ]
机构
[1] Indian Inst Technol, Delhi, India
[2] Indian Inst Technol, Kanpur, Uttar Pradesh, India
关键词
RECOGNITION; SURFACE;
D O I
10.1109/WACV.2018.00026
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
We present a method for discovering never-seen-before objects in 3D point clouds obtained from sensors like Microsoft Kinect. We generate supervoxels directly from the point cloud data and use them with a Siamese network, built on a recently proposed 3D convolutional neural network architecture. We use known objects to train a non-linear embedding of supervoxels, by optimizing the criteria that supervoxels which fall on the same object should be closer than those which fall on different objects, in the embedding space. We test on unknown objects, which were not seen during training, and perform clustering in the learned embedding space of supervoxels to effectively perform novel object discovery. We validate the method with extensive experiments, quantitatively showing that it can discover numerous unseen objects while being trained on only a few dense 3D models. We also show very good qualitative results of object discovery in point cloud data when the test objects, either specific instances or even categories, were never seen during training.
引用
收藏
页码:179 / 188
页数:10
相关论文
共 50 条
  • [1] A Large-Scale 3D Object Recognition dataset
    Solund, Thomas
    Buch, Anders Glent
    Kruger, Norbert
    Aanaes, Henrik
    [J]. PROCEEDINGS OF 2016 FOURTH INTERNATIONAL CONFERENCE ON 3D VISION (3DV), 2016, : 73 - 82
  • [2] 3D Object Detection on large-scale dataset
    Zhao, Yan
    Zhu, Jihong
    Liang, Haoyu
    Chen, Lyujie
    [J]. 2021 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2021,
  • [3] ObjectNet3D: A Large Scale Database for 3D Object Recognition
    Xiang, Yu
    Kim, Wonhui
    Chen, Wei
    Ji, Jingwei
    Choy, Christopher
    Su, Hao
    Mottaghi, Roozbeh
    Guibas, Leonidas
    Savarese, Silvio
    [J]. COMPUTER VISION - ECCV 2016, PT VIII, 2016, 9912 : 160 - 176
  • [4] BigBIRD: A Large-Scale 3D Database of Object Instances
    Singh, Arjun
    Sha, James
    Narayan, Karthik S.
    Achim, Tudor
    Abbeel, Pieter
    [J]. 2014 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA), 2014, : 509 - 516
  • [5] 3D Measurement of Large-scale Object Using Independent Sensors
    Liu Yong
    Jia Yuan
    Jiang Yong
    Luo Xia
    [J]. THREE-DIMENSIONAL IMAGING, VISUALIZATION, AND DISPLAY 2017, 2017, 10219
  • [6] AutoRecon: Automated 3D Object Discovery and Reconstruction
    Wang, Yuang
    He, Xingyi
    Peng, Sida
    Lin, Haotong
    Bao, Hujun
    Zhou, Xiaowei
    [J]. 2023 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2023, : 21382 - 21391
  • [7] Large 3D Object FDTD Simulations
    Rudnicki, Janusz
    Sypniewski, Maciej
    [J]. 2012 19th International Conference on Microwave Radar and Wireless Communications (MIKON), Vols 1 and 2, 2012, : 505 - 507
  • [8] Large-Scale Unsupervised Object Discovery
    Vo, Huy V.
    Sizikova, Elena
    Schmid, Cordelia
    Perez, Patrick
    Ponce, Jean
    [J]. ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 34 (NEURIPS 2021), 2021, 34
  • [9] 3D object representation using transform and scale invariant 3D features
    Akagunduz, Erdem
    Ulusoy, Ilkay
    [J]. 2007 IEEE 11TH INTERNATIONAL CONFERENCE ON COMPUTER VISION, VOLS 1-6, 2007, : 55 - 62
  • [10] Unsupervised Discovery of Object Classes in 3D Outdoor Scenarios
    Moosmann, Frank
    Sauerland, Miro
    [J]. 2011 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION WORKSHOPS (ICCV WORKSHOPS), 2011,