KinshipGAN: Synthesizing of Kinship Faces From Family Photos by Regularizing a Deep Face Network

TL;DR

This paper introduces KinshipGAN, a novel face synthesis model that generates kinship faces from family photos by regularizing a deep face network to overcome dataset scarcity and improve stability.

Contribution

The paper proposes a kinship face generator with regularization techniques, integrating a pre-trained face model and cycle-domain transformation for enhanced synthesis quality.

Findings

Improved kinship face synthesis performance over baseline models

Effective handling of limited kinship datasets through regularization

Promising perceptual results demonstrated on FIW dataset

Abstract

In this paper, we propose a kinship generator network that can synthesize a possible child face by analyzing his/her parent's photo. For this purpose, we focus on to handle the scarcity of kinship datasets throughout the paper by proposing novel solutions in particular. To extract robust features, we integrate a pre-trained face model to the kinship face generator. Moreover, the generator network is regularized with an additional face dataset and adversarial loss to decrease the overfitting of the limited samples. Lastly, we adapt cycle-domain transformation to attain a more stable results. Experiments are conducted on Families in the Wild (FIW) dataset. The experimental results show that the contributions presented in the paper provide important performance improvements compared to the baseline architecture and our proposed method yields promising perceptual results.