End‐to‐end learning for arbitrary image style transfer
Y.B. Yoon, Minjun Kim, Hyun‐Chul Choi · Electronics Letters · 2018
Real‐time arbitrary style transfer is based on a feed‐forward network, which consists of a pre‐trained encoder, a feature transformer, and a trainable decoder. However, the previous approach has some degrade in style quality of output image because the pre‐trained encoder is not optimised for image style transfer but originally for image classification task. An end‐to‐end learning scheme is introduced that optimises the encoder as well as the decoder for the task of arbitrary image style transfer. Experiments conducted with a public database proves that the style transfer network trained with the end‐to‐end learning scheme outperforms the network with a fixed encoder in terms of minimising both content and style losses and quality of the stylised images.