Recent advances in implicit representation-based 3D shape generation

被引:0
|
作者
Jia-Mu Sun
Tong Wu
Lin Gao
机构
[1] Chinese Academy of Sciences,Institute of Computing Technology
[2] University of Chinese Academy of Sciences,undefined
来源
Visual Intelligence | / 2卷 / 1期
关键词
Generative models; 3D shape representations; Geometry learning; Deep learning;
D O I
10.1007/s44267-024-00042-1
中图分类号
学科分类号
摘要
Various techniques have been developed and introduced to address the pressing need to create three-dimensional (3D) content for advanced applications such as virtual reality and augmented reality. However, the intricate nature of 3D shapes poses a greater challenge to their representation and generation than standard two-dimensional (2D) image data. Different types of representations have been proposed in the literature, including meshes, voxels and implicit functions. Implicit representations have attracted considerable interest from researchers due to the emergence of the radiance field representation, which allows the simultaneous reconstruction of both geometry and appearance. Subsequent work has successfully linked traditional signed distance fields to implicit representations, and more recently the triplane has offered the possibility of generating radiance fields using 2D content generators. Many articles have been published focusing on these particular areas of research. This paper provides a comprehensive analysis of recent studies on implicit representation-based 3D shape generation, classifying these studies based on the representation and generation architecture employed. The attributes of each representation are examined in detail. Potential avenues for future research in this area are also suggested.
引用
收藏
相关论文
共 50 条
  • [1] Deep Implicit Templates for 3D Shape Representation
    Zheng, Zerong
    Yu, Tao
    Dai, Qionghai
    Liu, Yebin
    [J]. 2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021, 2021, : 1429 - 1439
  • [2] Sparse representation-based 3D model retrieval
    Cao, Qun
    An, Yang
    Shi, Yingdi
    Zhu, Xiaorong
    [J]. MULTIMEDIA TOOLS AND APPLICATIONS, 2017, 76 (19) : 20069 - 20079
  • [3] Sparse representation-based 3D model retrieval
    Qun Cao
    Yang An
    Yingdi Shi
    Xiaorong Zhu
    [J]. Multimedia Tools and Applications, 2017, 76 : 20069 - 20079
  • [4] 3D Shape Generation with Grid-based Implicit Functions
    Ibing, Moritz
    Lim, Isaak
    Kobbelt, Leif
    [J]. 2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021, 2021, : 13554 - 13563
  • [5] Multiresolution Deep Implicit Functions for 3D Shape Representation
    Chen, Zhang
    Zhang, Yinda
    Genova, Kyle
    Fanello, Sean
    Bouaziz, Sofien
    Hane, Christian
    Du, Ruofei
    Keskin, Cem
    Funkhouser, Thomas
    Tang, Danhang
    [J]. 2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021), 2021, : 13067 - 13076
  • [6] Shape Normalization of 3D Models Using Weighted Implicit Shape Representation
    Jin, Xun
    Kim, Jong-weon
    [J]. INTERNATIONAL CONFERENCE ON INFORMATICS, CONTROL AND AUTOMATION (ICA 2015), 2015, : 200 - 204
  • [7] EXIM: A Hybrid Explicit-Implicit Representation for Text-Guided 3D Shape Generation
    Liu, Zhengzhe
    Hu, Jingyu
    Hui, Ka-Hei
    Qi, Xiaojuan
    Cohen-Or, Daniel
    Fu, Chi-Wing
    [J]. ACM TRANSACTIONS ON GRAPHICS, 2023, 42 (06):
  • [8] Contributive Representation-Based Reconstruction for Online 3D Action Recognition
    Tabejamaat, Mohsen
    Mohammadzade, Hoda
    [J]. INTERNATIONAL JOURNAL OF PATTERN RECOGNITION AND ARTIFICIAL INTELLIGENCE, 2021, 35 (02)
  • [9] Towards Implicit Text-Guided 3D Shape Generation
    Liu, Zhengzhe
    Wang, Yi
    Qi, Xiaojuan
    Fu, Chi-Wing
    [J]. 2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022), 2022, : 17875 - 17885
  • [10] Recent Advances in 3D Medical Image Generation and Analysis
    Deserno , Thomas M.
    Handels, Heinz
    Meinzer, Hans-Peter
    Tolxdorff, Thomas
    [J]. CURRENT MEDICAL IMAGING REVIEWS, 2013, 9 (02) : 77 - 78