Stylizing Video by Example

被引:54
作者
Jamriska, Ondrej [1 ]
Sochorova, Sarka [1 ]
Texler, Ondrej [1 ]
Lukac, Michal [2 ]
Fiser, Jakub [2 ]
Lu, Jingwan [2 ]
Shechtman, Eli [2 ]
Sykora, Daniel [1 ]
机构
[1] Czech Tech Univ, Fac Elect Engn, Prague, Czech Republic
[2] Adobe Res, San Francisco, CA USA
来源
ACM TRANSACTIONS ON GRAPHICS | 2019年 / 38卷 / 04期
关键词
style transfer;
D O I
10.1145/3306346.3323006
中图分类号
TP31 [计算机软件];
学科分类号
081202 ; 0835 ;
摘要
We introduce a new example-based approach to video stylization, with a focus on preserving the visual quality of the style, user controllability and applicability to arbitrary video. Our method gets as input one or more keyframes that the artist chooses to stylize with standard painting tools. It then automatically propagates the stylization to the rest of the sequence. To facilitate this while preserving visual quality, we developed a new type of guidance for state-of-art patch-based synthesis, that can be applied to any type of video content and does not require any additional information besides the video itself and a user-specified mask of the region to be stylized. We further show a temporal blending approach for interpolating style between keyframes that preserves texture coherence, contrast and high frequency details. We evaluate our method on various scenes from real production setting and provide a thorough comparison with prior art.
引用
收藏
页数:11
相关论文
共 66 条
  • [1] [Anonymous], 2016, P IEEE C COMPUTER VI
  • [2] [Anonymous], P 3 INT C LEARNING R
  • [3] [Anonymous], P JOINT S COMP AESTH
  • [4] [Anonymous], 2018, INT J COMPUT VISION, DOI DOI 10.1007/s11263-018-1089-z
  • [5] [Anonymous], 2012, P S NONPHOTOREALISTI
  • [6] [Anonymous], 2018, ADV NEURAL INFORM PR, DOI DOI 10.1109/CVPRW.2018.00151
  • [7] [Anonymous], ACM T GRAPHICS
  • [8] [Anonymous], 2017, PROC CVPR IEEE, DOI DOI 10.1109/CVPR.2017.632
  • [9] [Anonymous], P SIGGRAPH ASIA
  • [10] [Anonymous], 2014, ACM T GRAPHICS TOG