MUSE: Textual Attributes Guided Portrait Painting Generation

TL;DR

MUSE is a novel neural network approach that generates personalized portraits from facial features and textual attributes, significantly improving visual fidelity and attribute preservation over existing methods.

Contribution

The paper introduces a stacked neural network architecture that incorporates textual attributes into portrait generation, enabling more expressive and accurate representations.

Findings

Inception Score increased by 6%

FID score decreased by 11%

78% attribute accuracy in generated portraits

Abstract

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.