After the success of the 1st edition of FRCSyn (Face Recognition Challenge in the Era of Synthetic Data) Workshop organized at IEEE/CVF WACV 2024, comes the 2nd edition of FRCSyn Workshop at IEEE/CVF CVPR 2024.
The summary paper of the WACV 2024 FRCSyn Challenge is available here.
To promote and advance the use of synthetic data for face recognition, we organize the Face Recognition Challenge in the Era of Synthetic Data (FRCSyn). This challenge is based on the FRCSyn Challenge organized within the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) 2024 and intends to provide an in-depth analysis of the following research questions:
- What are the limits of face recognition technology trained only with synthetic data?
- Can the use of synthetic data be beneficial to solve/reduce the current limitations existed in face recognition technology.
This is a novel and very important research line nowadays due to the recent discontinuation of face recognition datasets due to privacy concerns. Furthermore, state-of-the-art face recognition technology has several limitations in terms of bias in demographic groups (e.g., ethnicity and gender), and lack of performance in challenging conditions such as large age gaps between enrolment and testing, pose variations, occlusions, etc.
The results achieved in the proposed challenge will allow to analyse in detail the improvements achieved while using synthetic data and the state-of-the-art performance of current face recognition technology in realistic operational scenarios, extracting very valuable contributions to advance in the field.
Main web: https://frcsyn.github.io/