The rapid progress of photorealistic synthesis techniques has reached a critical point where the boundary between real and manipulated images starts to blur. Recently, a mega-scale deep face forgery dataset, ForgeryNet which comprised of 2.9 million images and 221,247 videos has been released. It is by far the largest publicly available in terms of data-scale, manipulations (7 image-level approaches, 8 video-level approaches), perturbations (36 independent and more mixed perturbations), and annotations (6.3 million classification labels, 2.9 million manipulated area annotations, and 221,247 temporal forgery segment labels). This paper reports methods and results in the ForgeryNet - Face Forgery Analysis Challenge 2021, which employs the ForgeryNet benchmark. The model evaluation is conducted offline on the private test set. A total of 186 participants registered for the competition, and 11 teams made valid submissions. We will analyze the top-ranked solutions and present some discussion on future work directions.
@article{arxiv.2112.08325,
title = {ForgeryNet -- Face Forgery Analysis Challenge 2021: Methods and Results},
author = {Yinan He and Lu Sheng and Jing Shao and Ziwei Liu and Zhaofan Zou and Zhizhi Guo and Shan Jiang and Curitis Sun and Guosheng Zhang and Keyao Wang and Haixiao Yue and Zhibin Hong and Wanguo Wang and Zhenyu Li and Qi Wang and Zhenli Wang and Ronghao Xu and Mingwen Zhang and Zhiheng Wang and Zhenhang Huang and Tianming Zhang and Ningning Zhao},
journal= {arXiv preprint arXiv:2112.08325},
year = {2021}
}