Example-based Turbulence Style Transfer

被引:30
|
作者
Sato, Syuhei [1 ]
Dobashi, Yoshinori [2 ,3 ]
Kim, Theodore [4 ]
Nishita, Tomoyuki [1 ,3 ,5 ]
机构
[1] DWANGO Co Ltd, Dwango CG Res, Tokyo, Japan
[2] Hokkaido Univ, Sapporo, Hokkaido, Japan
[3] Dwango CG Res, Tokyo, Japan
[4] Pixar Animat Studios, Emeryville, CA USA
[5] Hiroshima Shudo Univ, Hiroshima, Japan
来源
ACM TRANSACTIONS ON GRAPHICS | 2018年 / 37卷 / 04期
关键词
fluid simulation; reusing existing fluid animations; incompressibility; texture synthesis; patch-based synthesis; NOISE;
D O I
10.1145/3197517.3201398
中图分类号
TP31 [计算机软件];
学科分类号
081202 ; 0835 ;
摘要
Generating realistic fluid simulations remains computationally expensive, and animators can expend enormous effort trying to achieve a desired motion. To reduce such costs, several methods have been developed in which high-resolution turbulence is synthesized as a post process. Since global motion can then be obtained using a fast, low-resolution simulation, less effort is needed to create a realistic animation with the desired behavior. While much research has focused on accelerating the low-resolution simulation, the problem controlling the behavior of the turbulent, high-resolution motion has received little attention. In this paper, we show that style transfer methods from image editing can be adapted to transfer the turbulent style of an existing fluid simulation onto a new one. We do this by extending example-based image synthesis methods to handle velocity fields using a combination of patch-based and optimization-based texture synthesis. This approach allows us to take into account the incompressibility condition, which we have found to be a important factor during synthesis. Using our method, a user can easily and intuitively create high-resolution fluid animations that have a desired turbulent motion.
引用
收藏
页数:9
相关论文
共 50 条
  • [1] Example-based Synthesis of Turbulence by Flow Field Style Transfer
    Sato, Syuhei
    Dobashi, Yoshinori
    Nishita, Tomoyuki
    [J]. IGGRAPH ASIA 2017 TECHNICAL BRIEFS (SA'17), 2017,
  • [2] Example-Based Image Textural Style Transfer
    Lo, Kai-Han
    Wang, Yu-Chiang Frank
    Hua, Kai-Lung
    [J]. IEEE MULTIMEDIA, 2016, 23 (04) : 59 - 66
  • [3] Example-based style synthesis
    Drori, I
    Cohen-Or, D
    Yeshurun, H
    [J]. 2003 IEEE COMPUTER SOCIETY CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, VOL II, PROCEEDINGS, 2003, : 143 - 150
  • [4] Example-based cosmetic transfer
    Tong, Wai-Shun
    Tang, Chi-Keung
    Brown, Michael S.
    Xu, Ying-Qing
    [J]. PACIFIC GRAPHICS 2007: 15TH PACIFIC CONFERENCE ON COMPUTER GRAPHICS AND APPLICATIONS, 2007, : 211 - +
  • [5] An Example-based Color Transfer and Style Enhancement Through Locally Neighbor Embedding
    Tao, Liu
    Deng, Daiguo
    Wu, Xuelian
    Zeng, Kun
    [J]. PROCEEDINGS OF 3RD INTERNATIONAL CONFERENCE ON MULTIMEDIA TECHNOLOGY (ICMT-13), 2013, 84 : 974 - 983
  • [6] Split and Match: Example-based Adaptive Patch Sampling for Unsupervised Style Transfer
    Frigo, Oriel
    Sabater, Neus
    Delon, Julie
    Hellier, Pierre
    [J]. 2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, : 553 - 561
  • [7] EXAMPLE-BASED VIDEO COLOR TRANSFER
    Yao, Chun-Han
    Chang, Chia-Yang
    Chien, Shao-Yi
    [J]. 2016 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA & EXPO (ICME), 2016,
  • [8] FaceBlit: Instant Real-time Example-based Style Transfer to Facial Videos
    Texler, Aneta
    Texler, Ondrej
    Kucera, Michal
    Chai, Menglei
    Sykora, Daniel
    [J]. PROCEEDINGS OF THE ACM ON COMPUTER GRAPHICS AND INTERACTIVE TECHNIQUES, 2021, 4 (01)
  • [9] Example-Based Image Color and Tone Style Enhancement
    Wang, Baoyuan
    Yu, Yizhou
    Xu, Ying-Qing
    [J]. ACM TRANSACTIONS ON GRAPHICS, 2011, 30 (04):
  • [10] Example-Based Color Transfer for Gradient Meshes
    Xiao, Yi
    Wan, Liang
    Leung, Chi-Sing
    Lai, Yu-Kun
    Wong, Tien-Tsin
    [J]. IEEE TRANSACTIONS ON MULTIMEDIA, 2013, 15 (03) : 549 - 560