We introduce PortraitGen, a powerful portrait video editing method that achieves consistent
and expressive stylization with multimodal prompts. Traditional portrait video editing …

Foundation models are predominantly trained in an unsupervised or self-supervised manner
on highly diverse and large-scale datasets, making them broadly applicable to various …

Generative models such as Large Language Models (LLM) and Multimodal Large
Language models (MLLMs) trained on massive web corpora can memorize and disclose …

Face recognition datasets are often collected by crawling Internet and without individuals'
consents, raising ethical and privacy concerns. Generating synthetic datasets for training …

This paper studies how to synthesize face images of non-existent persons, to create a
dataset that allows effective training of face recognition (FR) models. Two important goals …

The accuracy of face recognition systems has improved significantly in the past few years,
thanks to the large amount of data collected and advancements in neural network …

We introduce Omni-ID, a novel facial representation designed specifically for generative
tasks. Omni-ID encodes holistic information about an individual's appearance across diverse …

Morphing Attack Detection (MAD) is a critical task in biometric security, aimed at identifying
and mitigating the risks posed by morphing attacks, where a face image is manipulated to …

Inspired by the effectiveness of 3D Gaussian Splatting (3DGS) in reconstructing detailed 3D
scenes within multi-view setups and the emergence of large 2D human foundation models …

Despite the considerable performance improvements of face recognition algorithms in
recent years, the same scientific advances responsible for this progress can also be used to …