Laplacian Pyramid Network

LapStyle, or Laplacian Pyramid Network, is a feed-forward style transfer method. It uses a Drafting Network to transfer global style patterns in low-resolution, and adopts higher resolution Revision Networks to revise local styles in a pyramid manner according to outputs of multi-level Laplacian filtering of the content image. Higher resolution details can be generated by stacking Revision Networks with multiple Laplacian pyramid levels. The final stylized image is obtained by aggregating outputs of all pyramid levels.

Specifically, we first generate image pyramid $\left(\bar{x}_{c}, r_{c}\right)$ from content image $x_{c}$ with the help of Laplacian filter. Rough low-resolution stylized image are then generated by the Drafting Network. Then the Revision Network generates stylized detail image in high resolution. Then the final stylized image is generated by aggregating the outputs pyramid. $L, C$ and $A$ in an image represent Laplacian, concatenate and aggregation operation separately.