Real-to-Cartoon translation

2 papers with code • 0 benchmarks • 0 datasets

Cartoonifying images


Greatest papers with code

CartoonGAN: Generative Adversarial Networks for Photo Cartoonization

mnicnc404/CartoonGan-tensorflow CVPR 2018

Two novel losses suitable for cartoonization are proposed: (1) a semantic content loss, which is formulated as a sparse regularization in the high-level feature maps of the VGG network to cope with substantial style variation between photos and cartoons, and (2) an edge-promoting adversarial loss for preserving clear edges.

Real-to-Cartoon translation