Futschik, DavidChai, MengleiCao, ChenMa, ChongyangStoliar, AlekseiKorolev, SergeyTulyakov, SergeyKučera, MichalSýkora, DanielKaplan, Craig S. and Forbes, Angus and DiVerdi, Stephen2019-05-202019-05-202019978-3-03868-078-9https://doi.org/10.2312/exp.20191074https://diglib.eg.org:443/handle/10.2312/exp20191074We present a learning-based style transfer algorithm for human portraits which significantly outperforms current state-of-the-art in computational overhead while still maintaining comparable visual quality. We show how to design a conditional generative adversarial network capable to reproduce the output of Fišer et al.'s patch-based method [FJS*17] that is slow to compute but can deliver state-of-the-art visual quality. Since the resulting end-to-end network can be evaluated quickly on current consumer GPUs, our solution enables first real-time high-quality style transfer to facial videos that runs at interactive frame rates. Moreover, in cases when the original algorithmic approach of Fišer et al. fails our network can provide a more visually pleasing result thanks to generalization. We demonstrate the practical utility of our approach on a variety of different styles and target subjects.Computing methodologiesNonphotorealistic rendering10.2312/exp.2019107433-42