GP-GAN: Gender Preserving GAN for Synthesizing Faces from Landmarks

TL;DR

This paper introduces GP-GAN, a novel generative model that synthesizes realistic face images from landmarks while preserving gender information, enabling improved face analysis and dataset augmentation.

Contribution

The paper presents GP-GAN, a gender-preserving GAN for face synthesis from landmarks, including a new UDeNet generator architecture and multiple loss functions to enhance gender retention.

Findings

GP-GAN effectively preserves gender during face synthesis.

The UDeNet generator improves synthesis quality.

Experiments outperform recent methods in face generation from landmarks.

Abstract

Facial landmarks constitute the most compressed representation of faces and are known to preserve information such as pose, gender and facial structure present in the faces. Several works exist that attempt to perform high-level face-related analysis tasks based on landmarks. In contrast, in this work, an attempt is made to tackle the inverse problem of synthesizing faces from their respective landmarks. The primary aim of this work is to demonstrate that information preserved by landmarks (gender in particular) can be further accentuated by leveraging generative models to synthesize corresponding faces. Though the problem is particularly challenging due to its ill-posed nature, we believe that successful synthesis will enable several applications such as boosting performance of high-level face related tasks using landmark points and performing dataset augmentation. To this end, a novel face-synthesis method known as Gender Preserving Generative Adversarial Network (GP-GAN) that is guided by adversarial loss, perceptual loss and a gender preserving loss is presented. Further, we propose a novel generator sub-network UDeNet for GP-GAN that leverages advantages of U-Net and DenseNet architectures. Extensive experiments and comparison with recent methods are performed to verify the effectiveness of the proposed method.