Learning Part Boundaries from 3D Point Clouds

被引:21
|
作者
Loizou, Marios [1 ,2 ]
Averkiou, Melinos [1 ,2 ]
Kalogerakis, Evangelos [3 ]
机构
[1] Univ Cyprus, Nicosia, Cyprus
[2] RISE CoE, Nicosia, Cyprus
[3] Univ Massachusetts, Amherst, MA 01003 USA
关键词
FEATURES;
D O I
10.1111/cgf.14078
中图分类号
TP31 [计算机软件];
学科分类号
081202 ; 0835 ;
摘要
We present a method that detects boundaries of parts in 3D shapes represented as point clouds. Our method is based on a graph convolutional network architecture that outputs a probability for a point to lie in an area that separates two or more parts in a 3D shape. Our boundary detector is quite generic: it can be trained to localize boundaries of semantic parts or geometric primitives commonly used in 3D modeling. Our experiments demonstrate that our method can extract more accurate boundaries that are closer to ground-truth ones compared to alternatives. We also demonstrate an application of our network to fine-grained semantic shape segmentation, where we also show improvements in terms of part labeling performance.
引用
收藏
页码:183 / 195
页数:13
相关论文
共 50 条
  • [1] Learning to Close the Loop from 3D Point Clouds
    Granstrom, Karl
    Schon, Thomas B.
    [J]. IEEE/RSJ 2010 INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS 2010), 2010, : 2089 - 2095
  • [2] Learning Generalizable Part-based Feature Representation for 3D Point Clouds
    Wei, Xin
    Gu, Xiang
    Sun, Jian
    [J]. ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 35 (NEURIPS 2022), 2022,
  • [3] DeepPipes: Learning 3D pipelines reconstruction from point clouds
    Cheng, Lili
    Wei, Zhuo
    Sun, Mingchao
    Xin, Shiqing
    Sharf, Andrei
    Li, Yangyan
    Chen, Baoquan
    Tu, Changhe
    [J]. GRAPHICAL MODELS, 2020, 111
  • [4] Extraction 3D Road Boundaries from Mobile Laser Scanning Point Clouds
    Fang, Lina
    Yang, Bisheng
    Chen, Chongcheng
    Fu, Huasheng
    [J]. PROCEEDINGS 2015 SECOND IEEE INTERNATIONAL CONFERENCE ON SPATIAL DATA MINING AND GEOGRAPHICAL KNOWLEDGE SERVICES (ICSDM 2015), 2015, : 162 - 165
  • [5] Review: Deep Learning on 3D Point Clouds
    Bello, Saifullahi Aminu
    Yu, Shangshu
    Wang, Cheng
    Adam, Jibril Muhmmad
    Li, Jonathan
    [J]. REMOTE SENSING, 2020, 12 (11)
  • [6] Learning Interpretable Representation for 3D Point Clouds
    Su, Feng-Guang
    Lin, Ci-Siang
    Wang, Yu-Chiang Frank
    [J]. 2020 25TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR), 2021, : 7470 - 7477
  • [7] Deep Learning for 3D Point Clouds: A Survey
    Guo, Yulan
    Wang, Hanyun
    Hu, Qingyong
    Liu, Hao
    Liu, Li
    Bennamoun, Mohammed
    [J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2021, 43 (12) : 4338 - 4364
  • [8] Learning persistent homology of 3D point clouds
    Zhou, Chi
    Dong, Zhetong
    Lin, Hongwei
    [J]. COMPUTERS & GRAPHICS-UK, 2022, 102 : 269 - 279
  • [9] AUTOMATED PART INSPECTION USING 3D POINT CLOUDS
    Wells, Lee J.
    Shafae, Mohammed S.
    Camelio, Jaime A.
    [J]. PROCEEDINGS OF THE ASME 8TH INTERNATIONAL MANUFACTURING SCIENCE AND ENGINEERING CONFERENCE - 2013, VOL 2, 2013,
  • [10] 3D shape from unorganized 3D point clouds
    Kamberov, G
    Kamberova, G
    Jain, A
    [J]. ADVANCES IN VISUAL COMPUTING, PROCEEDINGS, 2005, 3804 : 621 - +