Facial Synthesis from Visual Attributes via Sketch using Multi-Scale Generators

TL;DR

This paper introduces a two-stage face synthesis framework that generates facial sketches from visual attributes and then produces face images from these sketches, leveraging GANs for improved realism and control.

Contribution

It proposes a novel stage-wise approach using two GANs to synthesize faces from attributes via sketches, differing from direct attribute-to-face methods.

Findings

Effective face synthesis from attributes demonstrated

Outperforms recent methods in quality and realism

Two-stage approach improves control and accuracy

Abstract

Automatic synthesis of faces from visual attributes is an important problem in computer vision and has wide applications in law enforcement and entertainment. With the advent of deep generative convolutional neural networks (CNNs), attempts have been made to synthesize face images from attributes and text descriptions. In this paper, we take a different approach, where we formulate the original problem as a stage-wise learning problem. We first synthesize the facial sketch corresponding to the visual attributes and then we generate the face image based on the synthesized sketch. The proposed framework, is based on a combination of two different Generative Adversarial Networks (GANs) - (1) a sketch generator network which synthesizes realistic sketch from the input attributes, and (2) a face generator network which synthesizes facial images from the synthesized sketch images with the help of facial attributes. Extensive experiments and comparison with recent methods are performed to verify the effectiveness of the proposed attribute-based two-stage face synthesis method.