Face Age Progression With Attribute Manipulation

TL;DR

This paper introduces FAWAM, a holistic model that generates face images at different ages while manipulating attributes, using GANs to model age-specific changes and preserve subject identity.

Contribution

The paper presents a novel combined approach for face aging and attribute manipulation using pyramidal GANs, addressing a gap in modeling age-specific facial changes with attribute control.

Findings

Model achieves significant qualitative improvements.

Quantitative results outperform existing methods.

Extensive analysis confirms robustness across datasets.

Abstract

Face is one of the predominant means of person recognition. In the process of ageing, human face is prone to many factors such as time, attributes, weather and other subject specific variations. The impact of these factors were not well studied in the literature of face aging. In this paper, we propose a novel holistic model in this regard viz., ``Face Age progression With Attribute Manipulation (FAWAM)", i.e. generating face images at different ages while simultaneously varying attributes and other subject specific characteristics. We address the task in a bottom-up manner, as two submodules i.e. face age progression and face attribute manipulation. For face aging, we use an attribute-conscious face aging model with a pyramidal generative adversarial network that can model age-specific facial changes while maintaining intrinsic subject specific characteristics. For facial attribute manipulation, the age processed facial image is manipulated with desired attributes while preserving other details unchanged, leveraging an attribute generative adversarial network architecture. We conduct extensive analysis in standard large scale datasets and our model achieves significant performance both quantitatively and qualitatively.