Anime Style Transfer With Spatially-Adaptive Normalization
Junjian Lian, Jinrong Cui · 2021
Image style transfer has always been a popular topic in the field of computer vision. Many researchers have achieved transfer image texture characteristics, such as converting real photos to painting styles. Different from these style transfer tasks, our target is to colorize the anime line art according to the color scheme of the given reference image. We transfer the color of the anime characters' hair, clothes, skin, etc. to another grayscale anime line art. In this paper, we propose a model based on Spatially-Adaptive (DE) Normalization (SPADE) to achieve anime style transfer. In addition, we use a data augmentation method to solve the "lazy" problem of neural networks.