Celeb-DF（v2）数据集包含真实和DeepFake合成视频，其视频质量与在线传播的视频质量相似。Celeb-DF（v2）数据集比以前的Celeb-DF（v1）有了很大的扩展，后者仅包含795个DeepFake视频。到目前为止，Celeb-DF包括从YouTube收集的590个原始视频，这些视频具有不同年龄，种族和性别的主题，以及5639个相应的DeepFake视频。

 
Green box: Real images, Red box: Corresponding DeepFake images.

Citation

@inproceedings{Celeb_DF_cvpr20,
author = {Yuezun Li and Pu Sun and Honggang Qi and Siwei Lyu},
booktitle = {IEEE Conference on Computer Vision and Patten Recognition (CVPR)},
title = {{Celeb-DF: A Large-scale Challenging Dataset for DeepFake Forensics}},
address = {Seattle, WA, United States},
year = {2020}, }

What is New?

Celeb-DF (v2) dataset contains real and DeepFake synthesized videos having similar visual quality on par with those circulated online. The Celeb-DF (v2) dataset is greatly extended from our previous Celeb-DF (v1), which only contains 795 DeepFake videos. To date, Celeb-DF includes 590 original videos collected from YouTube with subjects of different ages, ethic groups and genders, and 5639 corresponding DeepFake videos.

Comparison with Other Datasets

 
See paper for details.

Average AUC of Detection Performance on Each Dataset

 
See paper for details.