该博客探讨了一种神经算法，它通过计算不同滤波器响应之间的相关性来捕获艺术风格，使用Gram矩阵表示风格统计。随着在网络中匹配更高层的风格表示，图像的局部结构在更大尺度上匹配，从而产生更平滑、连续的视觉效果。内容与风格之间的权衡调整可以创建视觉上吸引人的合成图像，既保留内容又体现风格特点。
Gatys, Leon A., Alexander S. Ecker, and Matthias Bethge. “A neural algorithm of artistic style.” arXiv preprint arXiv:1508.06576 (2015). (Citations: 99).
1 Motivation
Given a content image and a style image, we want to obtain a synthesised image which matches the content representation of the content image and the style representation of the style image.
2 Method
We compute the correlations between the different filter responses as the style statistics, where the expectation is taken over the spatial extend of the input image. These feature correlations are given by the Gram matrix G ∈ R^{D×D}.
最低0.47元/天 解锁文章
扫一扫
880
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
