We propose a novel approach, MUSE, to illustrate textual attributes visually via portrait generation. MUSE takes a set of attributes written in text, in addition to facial features extracted from a photo of the subject as input. We propose 11 attribute types to represent inspirations from a subject's profile, emotion, story, and environment. We propose a novel stacked neural network architecture by extending an image-to-image generative model to accept textual attributes. Experiments show that our approach significantly outperforms several state-of-the-art methods without using textual attributes, with Inception Score score increased by 6% and Fr\'echet Inception Distance (FID) score decreased by 11%, respectively. We also propose a new attribute reconstruction metric to evaluate whether the generated portraits preserve the subject's attributes. Experiments show that our approach can accurately illustrate 78% textual attributes, which also help MUSE capture the subject in a more creative and expressive way.
@article{arxiv.2011.04761,
title = {MUSE: Textual Attributes Guided Portrait Painting Generation},
author = {Xiaodan Hu and Pengfei Yu and Kevin Knight and Heng Ji and Bo Li and Honghui Shi},
journal= {arXiv preprint arXiv:2011.04761},
year = {2021}
}