Login | Register

Wavelet-based Multi-level GANs for Facial Attributes Editing


Wavelet-based Multi-level GANs for Facial Attributes Editing

Shao, Jun ORCID: https://orcid.org/0000-0002-8620-1123 (2021) Wavelet-based Multi-level GANs for Facial Attributes Editing. Masters thesis, Concordia University.

[thumbnail of Shao_MCSc_F2021.pdf]
Text (application/pdf)
Shao_MCSc_F2021.pdf - Accepted Version
Available under License Spectrum Terms of Access.


Recently, both face aging and expression translation have received increasing attention from the computer vision community due to their wide applications in the real world.

For face aging, age accuracy and identity preserving are two important indicators. Previous works usually rely on an extra pre-trained module for identity preserving and multi-level discriminators for fine-grained features extraction. In this work, we propose a cycle-consistent loss based method for face aging with wavelet-based multi-level facial attributes extraction from both generator and discriminators.
The proposed model consists of one generator with three-level encoders and three levels of discriminators with an age and a gender classifier on top of each discriminator.
Experiment results on both MORPH and CACD show that the application of multi-level generator can improve the identity preserving effects in face aging and reduce the training time significantly by eliminating the rely of an identity preserving module.
Our model can outperform most of the existing approaches including the state-of-the-art techniques on two benchmark aging databases in terms of both aging accuracy and identity verification confidence, demonstrating the effectiveness and superiority of our method.

In real world, expression synthesis is hard due to the non-linear properties of facial skin and muscle caused by different expressions. A recent study showed that the practice of using the same generator for both forward prediction and backward reconstruction as in current conditional GANs would force the generator to leave a potential "noise" in the generated images, therefore hindering the use of the images for further tasks. To eliminate the interference and break the unwanted link between the first and second translation, we design a parallel training mechanism with two generators that perform the same first translation but work as a reconstruction model for each other. Additionally, inspired by the successful application of wavelet-based multi-level Generative Adversarial Networks(GANs) in face aging and progressive training in geometric conversion, we further design a novel wavelet-based multi-level Generative Adversarial Network (WP2-GAN) for expression translation with a large gap based on a progressive and parallel training strategy. Extensive experiments show the effectiveness of our approach for expression translation compared with the state-of-the-art models by synthesizing photo-realistic images with high fidelity and vivid expression effect.

Divisions:Concordia University > Gina Cody School of Engineering and Computer Science > Computer Science and Software Engineering
Item Type:Thesis (Masters)
Authors:Shao, Jun
Institution:Concordia University
Degree Name:M. Comp. Sc.
Program:Computer Science
Date:November 2021
Thesis Supervisor(s):Bui, Tien D. and Krzyzak, Adam
ID Code:990008
Deposited By: Jun Shao
Deposited On:16 Jun 2022 15:11
Last Modified:16 Jun 2022 15:11
All items in Spectrum are protected by copyright, with all rights reserved. The use of items is governed by Spectrum's terms of access.

Repository Staff Only: item control page

Downloads per month over past year

Research related to the current document (at the CORE website)
- Research related to the current document (at the CORE website)
Back to top Back to top