5 papers
Happy Young Women, Grumpy Old Men? Emotion-Driven Demographic Biases in Synthetic Face Generation
Mengting Wei, Aditya Gulati, Guoying Zhao +1
Synthetic faces from text-to-image (T2I) models pervade digital media, yet their demographic biases under emotionally conditioned prompts remain poorly understood. We aim to system…
MagicPortrait: Temporally Consistent Face Reenactment with 3D Geometric Guidance
Mengting Wei, Yante Li, Tuomas Varanka +2
In this study, we propose a method for video face reenactment that integrates a 3D face parametric model into a latent diffusion framework, aiming to improve shape consistency and…
Towards Consistent and Controllable Image Synthesis for Face Editing
Mengting Wei, Tuomas Varanka, Yante Li +3
Face editing methods, essential for tasks like virtual avatars, digital human synthesis and identity preservation, have traditionally been built upon GAN-based techniques, while re…
MagicFace: High-Fidelity Facial Expression Editing with Action-Unit Control
Mengting Wei, Tuomas Varanka, Xingxun Jiang +2
We address the problem of facial expression editing by controling the relative variation of facial action-unit (AU) from the same person. This enables us to edit this specific pers…
Towards Localized Fine-Grained Control for Facial Expression Generation
Tuomas Varanka, Huai-Qian Khor, Yante Li +4
Generative models have surged in popularity recently due to their ability to produce high-quality images and video. However, steering these models to produce images with specific a…