Transport-Based Neural Style Transfer for Smoke Simulations

被引:34
作者
Kim, Byungsoo [1 ]
Azevedo, Vinicius C. [1 ]
Gross, Markus [1 ]
Solenthaler, Barbara [1 ]
机构
[1] Swiss Fed Inst Technol, Zurich, Switzerland
来源
ACM TRANSACTIONS ON GRAPHICS | 2019年 / 38卷 / 06期
基金
瑞士国家科学基金会;
关键词
physically-based animation; fluid simulation; neural style transfer;
D O I
10.1145/3355089.3356560
中图分类号
TP31 [计算机软件];
学科分类号
081202 ; 0835 ;
摘要
Artistically controlling fluids has always been a challenging task. Optimization techniques rely on approximating simulation states towards target velocity or density field configurations, which are often handcrafted by artists to indirectly control smoke dynamics. Patch synthesis techniques transfer image textures or simulation features to a target flow field. However, these are either limited to adding structural patterns or augmenting coarse flows with turbulent structures, and hence cannot capture the full spectrum of different styles and semantically complex structures. In this paper, we propose the first Transport-based Neural Style Transfer (TNST) algorithm for volumetric smoke data. Our method is able to transfer features from natural images to smoke simulations, enabling general content-aware manipulations ranging from simple patterns to intricate motifs. The proposed algorithm is physically inspired, since it computes the density transport from a source input smoke to a desired target configuration. Our transport-based approach allows direct control over the divergence of the stylization velocity field by optimizing incompressible and irrotational potentials that transport smoke towards stylization. Temporal consistency is ensured by transporting and aligning subsequent stylized velocities, and 3D reconstructions are computed by seamlessly merging stylizations from different camera viewpoints.
引用
收藏
页数:11
相关论文
共 55 条
  • [1] [Anonymous], 2017, DISTILL
  • [2] [Anonymous], 2016, EUR C COMP VIS
  • [3] [Anonymous], ACM SIGGRAPH 2005 PA
  • [4] [Anonymous], 2019, Computer Graphics Forum
  • [5] [Anonymous], P ACM SIGGR EUR SCA
  • [6] [Anonymous], COMPUTER GRAPHICS FO
  • [7] [Anonymous], ACM TOG
  • [8] [Anonymous], ACM SIGGRAPH 2004
  • [9] [Anonymous], 2004, COMPUTER ANIMATION 2, DOI DOI 10.1145/1028523.1028549
  • [10] [Anonymous], 2015, NATURE COMMUNICATION