Learning Fuzzy Set Representations of Partial Shapes on Dual Embedding Spaces

被引:3
|
作者
Sung, Minhyuk [1 ]
Dubrovina, Anastasia [1 ]
Kim, Vladimir G. [2 ]
Guibas, Leonidas [1 ]
机构
[1] Stanford Univ, Stanford, CA 94305 USA
[2] Adobe Res, San Jose, CA USA
基金
美国国家科学基金会;
关键词
CCS Concepts; Machine learning approaches; Shape analysis; • Computing methodologies → Shape modeling;
D O I
10.1111/cgf.13492
中图分类号
TP31 [计算机软件];
学科分类号
081202 ; 0835 ;
摘要
Modeling relations between components of 3D objects is essential for many geometry editing tasks. Existing techniques commonly rely on labeled components, which requires substantial annotation effort and limits components to a dictionary of predefined semantic parts. We propose a novel framework based on neural networks that analyzes an uncurated collection of 3D models from the same category and learns two important types of semantic relations among full and partial shapes: complementarity and interchangeability. The former helps to identify which two partial shapes make a complete plausible object, and the latter indicates that interchanging two partial shapes from different objects preserves the object plausibility. Our key idea is to jointly encode both relations by embedding partial shapes as fuzzy sets in dual embedding spaces. We model these two relations as fuzzy set operations performed across the dual embedding spaces, and within each space, respectively. We demonstrate the utility of our method for various retrieval tasks that are commonly needed in geometric modeling interfaces.
引用
收藏
页码:71 / 81
页数:11
相关论文
共 50 条
  • [11] A note on embedding and generating dual polar spaces
    Cooperstein, B. N.
    Shult, E. E.
    ADVANCES IN GEOMETRY, 2001, 1 (01) : 37 - 48
  • [12] Fuzzy Relations and Fuzzy Functions in Partial Fuzzy Set Theory
    Dankova, Martina
    ADVANCES IN FUZZY LOGIC AND TECHNOLOGY 2017, VOL 1, 2018, 641 : 563 - 573
  • [13] Fuzzy set representations of some quantum structures
    Dvurecenskij, A
    FUZZY SETS AND SYSTEMS, 1999, 101 (01) : 67 - 78
  • [14] Representations through a monoid on the set of fuzzy implications
    Vemuri, Nageswara Rao
    Jayaram, Balasubramaniam
    FUZZY SETS AND SYSTEMS, 2014, 247 : 51 - 67
  • [15] DeepCurrents: Learning Implicit Representations of Shapes with Boundaries
    Palmer, David
    Smirnov, Dmitriy
    Wang, Stephanie
    Chern, Albert
    Solomon, Justin
    2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022), 2022, : 18644 - 18654
  • [16] Towards Fuzzy Partial Set Theory
    Behounek, Libor
    Dankova, Martina
    INFORMATION PROCESSING AND MANAGEMENT OF UNCERTAINTY IN KNOWLEDGE-BASED SYSTEMS, IPMU 2016, PT II, 2016, 611 : 482 - 494
  • [17] On Strong Fuzzy Partial Metric Spaces
    Guner, Elif
    Aygun, Halis
    MATHEMATICAL METHODS FOR ENGINEERING APPLICATIONS, ICMASE 2023, 2024, 439 : 253 - 266
  • [18] Rep the Set: Neural Networks for Learning Set Representations
    Skianis, Konstantinos
    Nikolentzos, Giannis
    Limnios, Stratis
    Vazirgiannis, Michalis
    INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND STATISTICS, VOL 108, 2020, 108
  • [19] ON EMBEDDING PROBLEMS OF FUZZY NUMBER SPACES .4.
    MING, M
    FUZZY SETS AND SYSTEMS, 1993, 58 (02) : 185 - 193
  • [20] A note on the embedding problem for multidimensional fuzzy number spaces
    Wu, CX
    Zhang, BK
    FUZZY SETS AND SYSTEMS, 2001, 121 (02) : 359 - 362