SeCGAN: Parallel Conditional Generative Adversarial Networks for Face Editing via Semantic Consistency

TL;DR

SeCGAN introduces a novel face editing method that uses semantic consistency without needing target masks, leading to more accurate attribute editing and high-quality image generation.

Contribution

SeCGAN proposes a dual-branch cGAN framework with semantic consistency loss, enabling effective face editing without target mask specification during inference.

Findings

Outperforms baselines in Target Attribute Recognition Rate

Maintains high quality metrics like FID and Inception Score

Effective semantic-guided face editing without target masks

Abstract

Semantically guided conditional Generative Adversarial Networks (cGANs) have become a popular approach for face editing in recent years. However, most existing methods introduce semantic masks as direct conditional inputs to the generator and often require the target masks to perform the corresponding translation in the RGB space. We propose SeCGAN, a novel label-guided cGAN for editing face images utilising semantic information without the need to specify target semantic masks. During training, SeCGAN has two branches of generators and discriminators operating in parallel, with one trained to translate RGB images and the other for semantic masks. To bridge the two branches in a mutually beneficial manner, we introduce a semantic consistency loss which constrains both branches to have consistent semantic outputs. Whilst both branches are required during training, the RGB branch is our primary network and the semantic branch is not needed for inference. Our results on CelebA and CelebA-HQ demonstrate that our approach is able to generate facial images with more accurate attributes, outperforming competitive baselines in terms of Target Attribute Recognition Rate whilst maintaining quality metrics such as self-supervised Fr\'{e}chet Inception Distance and Inception Score.