VideoForensicsHQ: Detecting High-quality Manipulated Face Videos

TL;DR

This paper introduces a high-quality face video forgery detection benchmark and proposes new detectors that combine spatial and temporal features, significantly improving detection accuracy and robustness against visually convincing fakes.

Contribution

The paper presents a novel high-quality benchmark dataset for face video forgery detection and introduces a new family of detectors that outperform existing methods.

Findings

Existing detectors struggle with visually convincing forgeries.

The new detectors outperform previous methods in accuracy.

The benchmark dataset enables better evaluation of detection techniques.

Abstract

There are concerns that new approaches to the synthesis of high quality face videos may be misused to manipulate videos with malicious intent. The research community therefore developed methods for the detection of modified footage and assembled benchmark datasets for this task. In this paper, we examine how the performance of forgery detectors depends on the presence of artefacts that the human eye can see. We introduce a new benchmark dataset for face video forgery detection, of unprecedented quality. It 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.