21 datasets found

FFIW dataset for face forgery detection

Face forgery detection using multi-scale wavelet transformer framework

The ForgeryNet dataset is a very large dataset for real-world face forgery detection, with 2.9 million images, 221,247 videos and 15 forgery approaches.

The DeeperForensics-1.0 (DF-1.0) dataset contains 60,000 videos and 17.6 million frames with 100 consented actors.

The Fair Forgery Detection (FairFD) dataset is a comprehensive racial bias evaluation benchmark for forgery detection, providing a large-scale dataset, fairness metrics, and...

A compact facial video forgery detection network for detecting manipulated faces in videos.

A novel large-scale dataset for face forgery detection in multi-person scenarios, comprising 10,000 high-quality forgery videos with an average of three human faces in each frame.

WildDeepfake [13] is a challenging real-world dataset for deepfake detection.

CelebDF [12] is a large-scale challenging dataset for deepfake forensics.

The GenFace dataset is a large-scale, diverse, and fine-grained high-fidelity deepfake dataset, which contains face forgery images generated by state-of-the-art synthesis...

Face forgery by deepfake is widely spread over the internet and has raised severe societal concerns. Recently, how to detect such forgery contents has become a hot research...

DeeperForensics-1.0 is a large-scale dataset for real-world face forgery detection, containing 60,000 videos and 17.6 million frames.

The Stable Diffusion dataset contains 100,000 images generated by the Stable Diffusion model.

The PGGAN dataset contains 100,000 faces generated by the Progressive GAN (PGGAN) model.

The Diverse Fake Face Dataset (DFFD) contains various types of real and fake images.

The paper proposes a unified face spoofing and forgery detection framework to solve the multi-dataset conflict problem, and the authors use five public autopilot datasets,...

The dataset contains real and fake face videos.

The paper proposes a unified face forgery detection framework to solve the multi-dataset conflict problem, and the authors use five public autopilot datasets, including...

The FFHQ dataset is a large dataset of high-quality face images with 1024 × 1024 resolution with variations in age, gender, and glasses.

Deepfakes have become a critical social problem, and detecting them is of utmost importance. The FaceForensics++ dataset offers fake video datasets. Most of the detection...