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
  • [41] Texture mapping via spherical multi-dimensional scaling
    Elad, A
    Keller, Y
    Kimmel, R
    SCALE SPACE AND PDE METHODS IN COMPUTER VISION, PROCEEDINGS, 2005, 3459 : 443 - 455
  • [42] Depth-aided Exemplar-based Hole Filling for DIBR View Synthesis
    Xu, Xuyuan
    Po, Lai-Man
    Cheung, Chun-Ho
    Feng, Litong
    Ng, Ka-Ho
    Cheung, Kwok-Wai
    2013 IEEE INTERNATIONAL SYMPOSIUM ON CIRCUITS AND SYSTEMS (ISCAS), 2013, : 2840 - 2843
  • [43] Multi-dimensional fast rule filter automata
    Fuchssteiner, B
    Kemper, A
    PHYSICA D, 1999, 129 (1-2): : 130 - 142
  • [44] Fast multi-dimensional NMR by minimal sampling
    Kupce, Eriks
    Freeman, Ray
    JOURNAL OF MAGNETIC RESONANCE, 2008, 191 (01) : 164 - 168
  • [45] Fast Multi-dimensional Polar Encoding and Decoding
    Mahdavifar, Hessam
    El-Khamy, Mostafa
    Lee, Jungwon
    Kang, Inyup
    2014 INFORMATION THEORY AND APPLICATIONS WORKSHOP (ITA), 2014, : 209 - 213
  • [46] Fast similarity join for multi-dimensional data
    Kalashnikov, Dmitri V.
    Prabhakar, Sunil
    INFORMATION SYSTEMS, 2007, 32 (01) : 160 - 177
  • [47] Multi-Objective Evolutionary Optimization of Exemplar-Based Classifiers: A PNN Test Case
    Rubio, Talitha
    Zhang, Tiantian
    Georgiopoulos, Michael
    Kaylani, Assem
    2011 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2011, : 1722 - 1731
  • [48] Multi-exemplar-guided image weathering via texture synthesis
    Du, Shiyin
    Song, Ying
    VISUAL COMPUTER, 2023, 39 (08): : 3691 - 3699
  • [49] Multi-exemplar-guided image weathering via texture synthesis
    Shiyin Du
    Ying Song
    The Visual Computer, 2023, 39 : 3691 - 3699
  • [50] Exemplar-Based Image Inpainting With Multi-Resolution Information and the Graph Cut Technique
    Liu, Huaming
    Bi, Xuehui
    Lu, Guanming
    Wang, Weilan
    IEEE ACCESS, 2019, 7 : 101641 - 101657