# Attribute-controlled face photo synthesis from simple line drawing

## TL;DR

This paper introduces a deep generative model using attribute-disentangled VAE to synthesize controllable, photorealistic face photos from simple line drawings, allowing user-specified attributes and style transfer.

## Contribution

It proposes an attribute-disentangled VAE framework that enhances controllability and disentanglement of face attributes in photo synthesis from line drawings.

## Key findings

- Model effectively disentangles face attributes from other variations.
- Synthesizes detailed, photorealistic face images with specified attributes.
- Enables style transfer for background and illumination.

## Abstract

Face photo synthesis from simple line drawing is a one-to-many task as simple line drawing merely contains the contour of human face. Previous exemplar-based methods are over-dependent on the datasets and are hard to generalize to complicated natural scenes. Recently, several works utilize deep neural networks to increase the generalization, but they are still limited in the controllability of the users. In this paper, we propose a deep generative model to synthesize face photo from simple line drawing controlled by face attributes such as hair color and complexion. In order to maximize the controllability of face attributes, an attribute-disentangled variational auto-encoder (AD-VAE) is firstly introduced to learn latent representations disentangled with respect to specified attributes. Then we conduct photo synthesis from simple line drawing based on AD-VAE. Experiments show that our model can well disentangle the variations of attributes from other variations of face photos and synthesize detailed photorealistic face images with desired attributes. Regarding background and illumination as the style and human face as the content, we can also synthesize face photos with the target style of a style photo.