Logos of the MPI Informatik and the Graphics, Vision and Video group


VideoForensicsHQ: Detecting High-quality Manipulated Face Videos

      Gereon Fox       Wentao Liu       Hyeongwoo Kim       Hans-Peter Seidel
      Mohamed Elgharib       Christian Theobalt
Max Planck Institute for Informatics


    In order to get access to the dataset, please send us a mail stating who you are and for what purpose you wish to use it. Please note that we wish to prevent the misuse of our dataset for unethical purposes, as stated in the license.

Abstract

New approaches to synthesize and manipulate face videos at very high quality have paved the way for new applications in computer animation, virtual and augmented reality and face video synthesis. There are concerns that they may be used maliciously, e.g. to manipulate videos of public figures, in order to spread false information. The research community therefore developed techniques for automated detection of modified imagery and assembled benchmark datasets of manipulated content. In this paper, we examine how the performance of detectors depends on the presence of artefacts that human observers would be able to detect as well. For this purpose we introduce a new benchmark dataset for face video forgery detection, providing visual manipulations of a quality that is unprecedented in this area. This dataset allows us to demonstrate that existing detection techniques have difficulties detecting fakes that reliably fool the human eye. We thus introduce a new family of detectors that examine combinations of spatial and temporal features and outperform existing approaches both in terms of detection accuracy and generalization to unseen fake generation methods and unseen identities.


Dataset

Dataset video