KinStyle: A Strong Baseline Photorealistic Kinship Face Synthesis with an Optimized StyleGAN Encoder

Abstract

High-fidelity kinship face synthesis is a challenging task due to the limited amount of kinship data available for training and low-quality images. In addition, it is also hard to trace the genetic traits between parents and children from those low-quality training images. To address these issues, we leverage the pre-trained state-of-the-art face synthesis model, StyleGAN2, for kinship face synthesis. To handle large age, gender and other attribute variations between the parents and their children, we conduct a thorough study of its rich latent spaces and different encoder architectures for an optimized encoder design to repurpose StyleGAN2 for kinship face synthesis. The obtained latent representation from our developed encoder pipeline with stage-wise training strikes a better balance of editability and synthesis fidelity for identity preserving and attribute manipulations than other compared approaches. With extensive subjective, quantitative, and qualitative evaluations, the proposed approach consistently achieves better performance in terms of facial attribute heredity and image generation fidelity than other compared state-of-the-art methods. This demonstrates the effectiveness of the proposed approach which can yield promising and satisfactory kinship face synthesis using only a single and straightforward encoder architecture.

This work was supported by the National Science and Technology Council under Grant 108-2628-E-001-003-MY3, 111-2628-E-001 -002 -MY3, 111-3114-E-194-001 -, 110-2221-E-001 -009 -MY2, 110-2634-F-002-051-, 111-2221-E-001-002-, and the Academia Sinica under Thematic Research Grant AS-TP-110-M07-2.