来源:知乎—林天威地址:https://zhuanlan.zhihu.com/p/384504389这篇专栏主要介绍我们团队(百度视觉技术部视频理解与编辑组)发表于CVPR 2021上的工作:”Drafting and Revision: Laplacian Pyramid Network for Fast High-Quality Artistic Style Transfer“。这篇论文主要针对当前的前馈风格化网络对于复杂的风格纹理迁移不理想的问题,提出了一种基于拉普拉斯金字塔的风格化网络,在风格化速度和质量上均有很大的提升,是我们在风格化方向的第一篇工作。相关的代码已经开源在PaddleGAN 欢迎大家试用和star。https://github.com/PaddlePaddle/PaddleGAN/blob/develop/docs/en_US/tutorials/lap_style.md
参考文献[1] Tamar Rott Shaham, Tali Dekel, and Tomer Michaeli. Singan: Learning a generative model from a single natural image. In Proceedings of the IEEE International Conference on Computer Vision, pages 4570–4580, 2019.[2] Nicholas Kolkin, Jason Salavon, and Gregory Shakhnarovich. Style transfer by relaxed optimal transport and self-similarity. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 10051–10060, 2019.[3] Liang J, Zeng H, Zhang L. High-Resolution Photorealistic Image Translation in Real-Time: A Laplacian Pyramid Translation Network[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2021: 9392-9400.