CtlGAN: Few-shot Artistic Portraits Generation with Contrastive Transfer Learning

arXiv:2203.08612v2 Announce Type: replace
Abstract: Generating artistic portraits is a challenging problem in computer vision. Existing portrait stylization models that generate good quality results are based on Image-to-Image Translation and require abundant data from both source and target domains. However, without enough data, these methods would result in overfitting. In this work, we propose CtlGAN, a new few-shot artistic portraits generation model with a novel contrastive transfer learning strategy. We adapt a pretrained StyleGAN in the source domain to a …

abstract arxiv computer computer vision cs.cv cs.gr data domains few-shot generate good however image image-to-image image-to-image translation overfitting portraits quality results transfer transfer learning translation type vision