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
  • [1] Emblaze: Illuminating Machine Learning Representations through Interactive Comparison of Embedding Spaces
    Sivaraman, Venkatesh
    Wu, Yiwei
    Perer, Adam
    IUI'22: 27TH INTERNATIONAL CONFERENCE ON INTELLIGENT USER INTERFACES, 2022, : 418 - 432
  • [2] Learning Word Representations from Scarce and Noisy Data with Embedding Sub-spaces
    Astudillo, Ramon F.
    Amir, Silvio
    Lin, Wang
    Silva, Mario
    Trancoso, Isabel
    PROCEEDINGS OF THE 53RD ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS AND THE 7TH INTERNATIONAL JOINT CONFERENCE ON NATURAL LANGUAGE PROCESSING, VOL 1, 2015, : 1074 - 1084
  • [3] Learning from imprecise granular data using trapezoidal fuzzy set representations
    Yager, Ronald R.
    SCALABLE UNCERTAINTY MANAGEMENT, PROCEEDINGS, 2007, 4772 : 244 - 254
  • [4] Learning Graph Representations with Embedding Propagation
    Garcia-Duran, Alberto
    Niepert, Mathias
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 30 (NIPS 2017), 2017, 30
  • [5] The Unique Representations of Fuzzy Entropy for a Finite Fuzzy Set
    Qing, Ming
    ADVANCES IN MECHATRONICS AND CONTROL ENGINEERING II, PTS 1-3, 2013, 433-435 : 766 - 769
  • [6] Boolean representations of fuzzy quantum spaces
    Navara, M
    FUZZY SETS AND SYSTEMS, 1997, 87 (02) : 201 - 207
  • [7] Learning Embedding Representations in High Dimensions
    Azar, Golara Ahmadi
    Emami, Melika
    Fletcher, Alyson
    Rangan, Sundeep
    2024 58TH ANNUAL CONFERENCE ON INFORMATION SCIENCES AND SYSTEMS, CISS, 2024,
  • [8] Fuzzy Partial Metric Spaces
    Amer, Fariha Jumaa
    COMPUTATIONAL ANALYSIS, AMAT 2015, 2016, 155 : 153 - 161
  • [9] Fuzzy partial metric spaces
    Gregori, Valentin
    Minana, Juan-Jose
    Miravet, David
    INTERNATIONAL JOURNAL OF GENERAL SYSTEMS, 2019, 48 (03) : 260 - 279
  • [10] A decomposition of the natural embedding spaces for the symplectic dual polar spaces
    De Bruyn, Bart
    LINEAR ALGEBRA AND ITS APPLICATIONS, 2007, 426 (2-3) : 462 - 477