pietromelzi / gandiffface Goto Github PK

You can download the GANDiffFace dataset described in the original paper here.

A bigger dataset with 10K identities has been released here.

The code is available for academic purposes only. To get access to the code, please follow the next steps:

1. Fill and sign the license available here
2. Send it to the following email addresses: [email protected] and [email protected]

We are using GANDiffFace databases to train face recognition systems within the FRCSyn Challenge series.

Our paper titled GANDiffFace: Controllable Generation of Synthetic Datasets for Face Recognition with Realistic Variations, has received the Best Paper Award at the 11th IEEE International Workshop on Analysis and Modeling of Faces and Gestures during ICCV 23.

Melzi, Pietro, Christian Rathgeb, Ruben Tolosana, Ruben Vera-Rodriguez, Dominik Lawatsch, Florian Domin, and Maxim Schaubert. "GANDiffFace: Controllable Generation of Synthetic Datasets for Face Recognition with Realistic Variations", Proceedings of the IEEE/CVF International Conference on Computer Vision Workshops, 2023. Link

Melzi, Pietro, Christian Rathgeb, Ruben Tolosana, Ruben Vera-Rodriguez, Aythami Morales, Dominik Lawatsch, Florian Domin, and Maxim Schaubert. "Synthetic Data for the Mitigation of Demographic Biases in Face Recognition", Proceedings of the IEEE International Joint Conference on Biometrics, 2023. Link

Melzi, Pietro, Ruben Tolosana, Ruben Vera-Rodriguez, Minchul Kim, Christian Rathgeb, Xiaoming Liu, Ivan DeAndres-Tame, Aythami Morales, Julian Fierrez, Javier Ortega-Garcia, et al. "FRCSyn Challenge at WACV 2024: Face Recognition Challenge in the Era of Synthetic Data", Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision Workshops, 2024. Link

Melzi, Pietro, Ruben Tolosana, Ruben Vera-Rodriguez, Minchul Kim, Christian Rathgeb, Xiaoming Liu, Ivan DeAndres-Tame, Aythami Morales, Julian Fierrez, Javier Ortega-Garcia, et al. "FRCSyn-onGoing: Benchmarking and Comprehensive Evaluation of Real and Synthetic Data to Improve Face Recognition Systems", Information Fusion, 2024.