Continuous Face Aging Generative Adversarial Networks

TL;DR

This paper introduces CFA-GAN, a novel model for continuous face aging that decomposes facial features into identity and age components, enabling realistic age progression within arbitrary age ranges.

Contribution

The paper presents the first continuous face aging model using GANs, decomposing features into identity and age basis, and introduces a new loss for identity preservation.

Findings

Demonstrates realistic continuous aging on MORPH dataset

Outperforms existing discrete aging models

Validates the effectiveness of feature decomposition approach

Abstract

Face aging is the task aiming to translate the faces in input images to designated ages. To simplify the problem, previous methods have limited themselves only able to produce discrete age groups, each of which consists of ten years. Consequently, the exact ages of the translated results are unknown and it is unable to obtain the faces of different ages within groups. To this end, we propose the continuous face aging generative adversarial networks (CFA-GAN). Specifically, to make the continuous aging feasible, we propose to decompose image features into two orthogonal features: the identity and the age basis features. Moreover, we introduce the novel loss function for identity preservation which maximizes the cosine similarity between the original and the generated identity basis features. With the qualitative and quantitative evaluations on MORPH, we demonstrate the realistic and continuous aging ability of our model, validating its superiority against existing models. To the best of our knowledge, this work is the first attempt to handle continuous target ages.