Age Progression with Style: Exploring Style-Based Generative Models for Progressive Face Aging
Vaishnavi M, Theekshana V, Raunak Kumari, Varshitha B S, Manasa Sandeep
Convolutional Neural Networks, Deep Learning, Facial Recognition,Image Synthesis, Image Translation, Python
As the look of the face normally changes with age, face aging is the method of rendering a given face to forecast its future appearance. This process is significant in the field of information forensics and security.Although conditional generative adversarial networks (cGANs) have shown some outstanding results, current cGAN-based approaches often learn distinct aging effects between any two different age groups using a single network. However, the inability to concurrently satisfy the three objectives of face aging—image quality, aging accuracy, and identity preservation—and thus, when the age gap widens, they frequently produce aged faces with obvious ghost effects.Motivated by the observation that faces progressively age with time,we describe an picture-to-image translation technique that trains a pre-trained GAN to encode directly true facial images in its latent space in accordance with a certain aging shift.To explicitly direct the encoder in producing the latent codes corresponding to the target age, we utilise a trained age regression network. Our method, which gives precise control over the generated image, considers the process of continuous ageing as a regression task between the input age and the intended goal age in this formulation. Our method also picks up new information as a non-linear path as opposed to approaches that just work in the latent space using a initial on the path controlling age.
Article Details
Unique Paper ID: 159627

Publication Volume & Issue: Volume 9, Issue 12

Page(s): 643 - 647
Article Preview & Download

Share This Article

Join our RMS

Conference Alert

NCSEM 2024

National Conference on Sustainable Engineering and Management - 2024

Last Date: 15th March 2024

Call For Paper

Volume 11 Issue 1

Last Date for paper submitting for Latest Issue is 25 June 2024

About Us enables door in research by providing high quality research articles in open access market.

Send us any query related to your research on

Social Media

Google Verified Reviews