Luis S. Luévano, PhD

Luis S. Luévano, PhD

Postdoctoral Researcher at the Idiap Research Institute. My current research interests are Face Recognition, Face Anti-Spoofing, Privacy, and Decentralized Machine Learning.

About me

Researcher focused in Computer Vision, Biometrics, Privacy, and Decentralized Machine Learning. I am currently working as a Postdoctal Researcher at the Idiap Research Institute in Switzerland. Previously, I worked as a Postdoctoral Research Fellow at the WIDE Team at Inria in the University of Rennes. My current research interests are Face Recognition, Face Anti-Spoofing, Privacy, and Decentralized Machine Learning. My PhD thesis work was on Binarized Neural Networks for Very Low Resolution Face Recognition for deployment on embedded devices.

🔬 Latest research

Identity-Preserving Aging and De-Aging of Faces in the StyleGAN Latent Space

Published in IEEE Joint Conference on Biometrics (IJCB) 2025, 2025

Face aging or de-aging with generative AI has gained significant attention for its applications in such fields like forensics, security, and media. However, most state of the art methods rely on conditional Generative Adversarial Networks (GANs), Diffusion-based models, or Visual Language Models (VLMs) to age or de-age faces based on predefined age categories and conditioning via loss functions, fine-tuning, or text prompts. The reliance on such conditioning leads to complex training requirements, increased data needs, and challenges in generating consistent results. Additionally, identity preservation is rarely taken into account or evaluated on a single face recognition system without any control or guarantees on whether identity would be preserved in a generated aged/de-aged face. In this paper, we propose to synthesize aged and de-aged faces via editing latent space of StyleGAN2 using a simple support vector modeling of aging/de-aging direction and several feature selection approaches. By using two state-of-the-art face recognition systems, we empirically find the identity preserving subspace within the StyleGAN2 latent space, so that an apparent age of a given face can changed while preserving the identity. We then propose a simple yet practical formula for estimating the limits on aging/de-aging parameters that ensures identity preservation for a given input face. Using our method and estimated parameters we have generated a public dataset of synthetic faces at different ages that can be used for benchmarking cross-age face recognition, age assurance systems, or systems for detection of synthetic images. Our code and dataset are available at the project page https://www.idiap.ch/paper/agesynth/

Recommended citation: Luis S. Luevano, Pavel Korshunov, Sébastien Marcel. "Identity-Preserving Aging and De-Aging of Faces in the StyleGAN Latent Space". IEEE Joint Conference on Biometrics (IJCB) 2025. to appear

SwiftFaceFormer: An Efficient and Lightweight Hybrid Architecture for Accurate Face Recognition Applications

Published in 2024 27th International Conference on Pattern Recognition (ICPR), 2024

With the growing breakthrough of deep learning-based face recognition, the development of lightweight models that achieve high accuracy with computational and memory efficiency has become paramount, especially for deployment on embedded domains. While Vision Transformers have shown significant promising results in various computer vision tasks, their adaptability to resource-constrained devices remains a significant challenge. This paper introduces SwiftFaceFormer, a new efficient, and lightweight family of face recognition models inspired by the hybrid SwiftFormer architecture. Our proposal not only retains the representational capacity of its predecessor but also introduces efficiency improvements, enabling enhanced face recognition performance at a fraction of the computational cost. We also propose to enhance the verification performance of our original most lightweight variant by using a training paradigm based on Knowledge Distillation. Through extensive experiments on several face benchmarks, the presented SwiftFaceFormer demonstrates high levels of accuracy compared to the original SwiftFormer model, and very competitive results with respect to state-of-the-art deep face recognition models, providing a suitable solution for real-time, on-device face recognition applications. Our code is available at https://github.com/Inria-CENATAV-Tec/SwiftFaceFormer

Recommended citation: Luis S. Luevano, Yoanna Martínez-Díaz, Heydi Méndez-Vázquez, Miguel Gonzalez-Mendoza, Davide Frey. "SwiftFaceFormer: An Efficient and Lightweight Hybrid Architecture for Accurate Face Recognition Applications". 2024 27th International Conference on Pattern Recognition (ICPR). https://link.springer.com/chapter/10.1007/978-3-031-78341-8_16

📰 News: