Editable Generative Adversarial Networks: Generating and Editing Faces Simultaneously

TL;DR

This paper introduces a unified GAN-based framework that can generate and edit high-quality face images with desired attributes simultaneously, improving over previous methods in image quality and editing performance.

Contribution

The authors propose a novel low-dimensional latent and attribute vector decomposition within a GAN framework for simultaneous face generation and editing.

Findings

Outperforms recent algorithms in image quality and editing performance

Achieves competitive attribute editing quality with state-of-the-art methods

Demonstrates effective simultaneous generation and editing of face images

Abstract

We propose a novel framework for simultaneously generating and manipulating the face images with desired attributes. While the state-of-the-art attribute editing technique has achieved the impressive performance for creating realistic attribute effects, they only address the image editing problem, using the input image as the condition of model. Recently, several studies attempt to tackle both novel face generation and attribute editing problem using a single solution. However, their image quality is still unsatisfactory. Our goal is to develop a single unified model that can simultaneously create and edit high quality face images with desired attributes. A key idea of our work is that we decompose the image into the latent and attribute vector in low dimensional representation, and then utilize the GAN framework for mapping the low dimensional representation to the image. In this way, we can address both the generation and editing problem by learning the generator. For qualitative and quantitative evaluations, the proposed algorithm outperforms recent algorithms addressing the same problem. Also, we show that our model can achieve the competitive performance with the state-of-the-art attribute editing technique in terms of attribute editing quality.