Fast Spatially Controllable Multi-dimensional Exemplar-Based Texture Synthesis and Morphing

被引:1
|
作者
Manke, Felix [1 ]
Wunsche, Burkhard [1 ]
机构
[1] Univ Auckland, Dept Comp Sci, Graph Grp, Auckland 1, New Zealand
关键词
COMPLEX; IMAGE;
D O I
10.1007/978-3-642-11840-1_2
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Texture synthesis and morphing are important techniques for efficiently creating realistic textures used in scientific and entertainment applications. In this paper we present a novel fast algorithm for multi-dimensional texture synthesis and morphing that is especially suitable for parallel architectures such as GPUs or direct volume rendering (DVR) hardware. Our proposed solution generalizes the synthesis process to support higher than three-dimensional synthesis and morphing. We introduce several improvements to previous 2D synthesis algorithms, such as new appearance space attributes and an improved jitter function. We then modify the synthesis algorithm to use it for texture morphing which can be applied to arbitrary many 2D input textures and can be spatially controlled using weight maps. Our results suggest that the algorithm produces higher quality textures than alternative algorithms with similar speed. Compared to higher quality texture synthesis algorithms, our solution is considerably faster and allows the synthesis of additional channels, such as transparencies and displacement maps, without affecting the running time of the synthesis at all. The method is easily extended to allow fast 3D synthesis and we show several novel examples and applications for morphed solid 3D textures. Overall the presented technique provides an excellent trade-off between speed and quality, is highly flexible, allows the use of arbitrary channels, can be extended to arbitrary dimensions, is suitable for a GPU-implementation, and can be effectively integrated into rendering frameworks such as DVR tools.
引用
收藏
页码:21 / 34
页数:14
相关论文
共 50 条
  • [31] Medical Visual Information Retrieval Based on Multi-Dimensional Texture Modeling
    Depeursinge, Adrien
    Miiller, Henning
    PROCEEDINGS OF THE 2ND EUROPEAN FUTURE TECHNOLOGIES CONFERENCE AND EXHIBITION 2011 (FET 11), 2011, 7 : 127 - 129
  • [32] Fast multi-dimensional Hadamard spectroscopy
    Kupce, E
    Freeman, R
    JOURNAL OF MAGNETIC RESONANCE, 2003, 163 (01) : 56 - 63
  • [33] Fast multi-dimensional NMR of proteins
    Kupce, E
    Freeman, R
    JOURNAL OF BIOMOLECULAR NMR, 2003, 25 (04) : 349 - 354
  • [34] Fast multi-dimensional NMR of proteins
    Eriks Kupče
    Ray Freeman
    Journal of Biomolecular NMR, 2003, 25 : 349 - 354
  • [35] Multi-class Semantic Video Segmentation with Exemplar-based Object Reasoning
    Liu, Buyu
    He, Xuming
    Gould, Stephen
    2015 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV), 2015, : 1014 - 1021
  • [36] An Exemplar-Based Multi-View Domain Generalization Framework for Visual Recognition
    Niu, Li
    Li, Wen
    Xu, Dong
    Cai, Jianfei
    IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2018, 29 (02) : 259 - 272
  • [37] Morphing and docking visualisation of biomolecular structures using Multi-Dimensional Scaling
    Veevers, Ruth
    Hayward, Steven
    JOURNAL OF MOLECULAR GRAPHICS & MODELLING, 2018, 82 : 108 - 116
  • [38] Exemplar based regular texture synthesis using LSTM
    Cai, Xiuxia
    Song, Bin
    Fang, Zhiqian
    PATTERN RECOGNITION LETTERS, 2019, 128 : 226 - 230
  • [39] Texture Classification using Multi-Dimensional LBP Variance
    Doshi, Niraj P.
    Schaefer, Gerald
    2013 SECOND IAPR ASIAN CONFERENCE ON PATTERN RECOGNITION (ACPR 2013), 2013, : 672 - 676
  • [40] An illumination invariant face recognition approach using exemplar-based synthesis technique
    Tan, T
    Kühnapfel, T
    Wongso, A
    Lim, FL
    COMPUTER ANALYSIS OF IMAGES AND PATTERNS, PROCEEDINGS, 2005, 3691 : 49 - 56