计算机视觉理论与实践 课件 8-图像风格化.pdf

Lec8 Image Stylization 人工智能引论实践课 ·AIPKU · 部分讲义来源与致谢 1. Leon A. Gatys, Alexander S. Ecker, Matthias Bethge. Image style transfer using convolutional neural networks. CVPR 2016. 2. Chuan Li, Michael Wand. Combining Markov random fields and convolutional neural networks for image synthesis. CVPR 2016. 3. Alex J. Champandard. Semantic Style Transfer and Turning Two-Bit Doodles into Fine Artworks. arXiv 2016. 4. Phillip Isola, Jun-Yan Zhu, Tinghui Zhou, Alexei A. Efros. Image-to-Image Translation with Conditional Adversarial Networks. CVPR 2017. 5. Jun-Yan Zhu, Taesung Park, Phillip Isola, Alexei A. Efros. Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks. ICCV 2017. 2 Background Image Style Transfer  Image stylization  Enrich content  Intensify representation  Convey emotion  Application  Social media  Graphic design 3 Background Image Style Transfer  Text stylization  Enrich content  Intensify representation BBS进站图片 logo设计 游戏主视觉 纪念衫设计 海报设计 5 Background Image Style Transfer  Color transfer  Texture transfer 6 Background Image Style Transfer  Color transfer  Texture transfer  Texture synthesis + structure constraint  Texture synthesis  Non-parametric methods  Parametric methods 7 Background Image Style Transfer  Color transfer  Texture transfer  Texture synthesis + structure constrai