GP-GAN: Gender Preserving GAN for Synthesizing Faces from Landmarks
Authors:
- 1 August 2018
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1079-1084
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 alone without the aid of face images. 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. Our code is available at: https://github.com/DetionDXlGP-GAN-Gender-Preserving-GAN-for-Synthesizing-Faces-from-LandmarksKeywords
All Related Versions
This publication has 15 references indexed in Scilit:
- Densely Connected Convolutional Networks2017
- Joint Face Detection and Alignment Using Multitask Cascaded Convolutional NetworksIEEE Signal Processing Letters, 2016
- Unconstrained face verification using deep CNN features2016
- Facial Landmark Detection by Deep Multi-task Learning2014
- Deep Convolutional Network Cascade for Facial Point Detection2013
- Robust Discriminative Response Map Fitting with Constrained Local Models2013
- Age Estimation and Face Verification Across Aging Using LandmarksIEEE Transactions on Information Forensics and Security, 2012
- Can facial metrology predict gender?2011
- Deformable Model Fitting by Regularized Landmark Mean-ShiftInternational Journal of Computer Vision, 2010
- Multiresolution gray-scale and rotation invariant texture classification with local binary patternsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2002