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
  • [41] Minimal Adversarial Examples for Deep Learning on 3D Point Clouds
    Kim, Jaeyeon
    Hua, Binh-Son
    Duc Thanh Nguyen
    Yeung, Sai-Kit
    [J]. 2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021), 2021, : 7777 - 7786
  • [42] Cross-Shape Attention for Part Segmentation of 3D Point Clouds
    Loizou, Marios
    Garg, Siddhant
    Petrov, Dmitry
    Averkiou, Melinos
    Kalogerakis, Evangelos
    [J]. COMPUTER GRAPHICS FORUM, 2023, 42 (05)
  • [43] Attentional Keypoint Detection on Point Clouds for 3D Object Part Segmentation
    Zhou, Feng
    Zhang, Qi
    Zhu, He
    Liu, Shibo
    Jiang, Na
    Cai, Xingquan
    Qi, Qianfang
    Hu, Yong
    [J]. APPLIED SCIENCES-BASEL, 2023, 13 (23):
  • [44] GRJointNET: Synergistic Completion and Part Segmentation on 3D Incomplete Point Clouds
    Gurses, Yigit
    Taspinar, Melisa
    Yurt, Mahmut
    Ozer, Sedat
    [J]. 29TH IEEE CONFERENCE ON SIGNAL PROCESSING AND COMMUNICATIONS APPLICATIONS (SIU 2021), 2021,
  • [45] From part to point cloud, the modelling of a 3D part
    Muntean, Diana
    Bologa, Octavian
    [J]. 9TH INTERNATIONAL CONFERENCE ON MANUFACTURING SCIENCE AND EDUCATION (MSE 2019): TRENDS IN NEW INDUSTRIAL REVOLUTION, 2019, 290
  • [46] Acquiring Mechanical Knowledge from 3D Point Clouds
    Li, Zijia
    Okada, Kei
    Inaba, Masayuki
    [J]. 2020 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS), 2020, : 8065 - 8072
  • [47] 3D Detection for Occluded Vehicles From Point Clouds
    Zhao, Kun
    Liu, Li
    Meng, Yu
    Liu, Hao
    Gu, Qing
    [J]. IEEE INTELLIGENT TRANSPORTATION SYSTEMS MAGAZINE, 2022, 14 (05) : 59 - 71
  • [48] 3D scene graph prediction from point clouds
    Fanfan WU
    Feihu YAN
    Weimin SHI
    Zhong ZHOU
    [J]. 虚拟现实与智能硬件(中英文), 2022, 4 (01) : 76 - 88
  • [49] 3D scene graph prediction from point clouds
    Wu, Fanfan
    Yan, Feihu
    Shi, Weimin
    Zhou, Zhong
    [J]. Virtual Reality and Intelligent Hardware, 2022, 4 (01): : 76 - 88
  • [50] Calculation the Spacing of Discontinuities from 3D Point Clouds
    Buyer, Andreas
    Schubert, Wulf
    [J]. ISRM EUROPEAN ROCK MECHANICS SYMPOSIUM EUROCK 2017, 2017, 191 : 270 - 278