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
  • [41] Dual representations of GL(infinity) and decomposition of Fock spaces
    Howe, RM
    JOURNAL OF PHYSICS A-MATHEMATICAL AND GENERAL, 1997, 30 (08): : 2757 - 2781
  • [42] Fuzzy and rough set - Combining fuzzy set and rough setfor inductive learning
    Jing, H
    Lu, JG
    Feng, S
    INTELLIGENT INFORMATION PROCESSING II, 2005, 163 : 143 - 146
  • [43] Pyramid Representations of the Set of Actions in Reinforcement Learning
    Iglesias, R.
    Alvarez-Santos, V.
    Rodriguez, M. A.
    Santos-Saavedra, D.
    Regueiro, C. V.
    Pardo, X. M.
    BIOINSPIRED COMPUTATION IN ARTIFICIAL SYSTEMS, PT II, 2015, 9108 : 203 - 212
  • [44] Learning knowledge graph embedding with a dual-attention embedding network
    Fang, Haichuan
    Wang, Youwei
    Tian, Zhen
    Ye, Yangdong
    EXPERT SYSTEMS WITH APPLICATIONS, 2023, 212
  • [45] Fuzzy optimization for portfolio selection based on Embedding Theorem in Fuzzy Normed Linear Spaces
    Solatikia, Farnaz
    Kilic, Erdem
    Weber, Gerhard Wilhelm
    ORGANIZACIJA, 2014, 47 (02) : 90 - 97
  • [46] Partial linear spaces with dual affine planes
    Cárdenas, H
    Lluis, E
    Raggi-Cárdenas, AG
    San Agustín, R
    COMMUNICATIONS IN ALGEBRA, 2002, 30 (02) : 603 - 617
  • [47] DUAL FUZZY NEIGHBORHOOD SPACES .1.
    MORSI, NN
    FUZZY SETS AND SYSTEMS, 1991, 44 (02) : 245 - 263
  • [48] Metric Spaces of Shapes and Geometries Constructed from Set Parametrized Functions
    Delfour, Michel C.
    NEW TRENDS IN SHAPE OPTIMIZATION, 2015, 166 : 57 - 101
  • [49] Dual Embedding Learning for Video Instance Segmentation
    Feng, Qianyu
    Yang, Zongxin
    Li, Peike
    Wei, Yunchao
    Yang, Yi
    2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION WORKSHOPS (ICCVW), 2019, : 717 - 720
  • [50] Differentiating Orlicz Spaces with Rectangles Having Fixed Shapes in a Set of Directions
    D'Aniello, Emma
    Moonens, Laurent
    ZEITSCHRIFT FUR ANALYSIS UND IHRE ANWENDUNGEN, 2020, 39 (04): : 461 - 473