A large-scale dataset for real-world face forgery detection.

DeeperForensics-1.0 is a large-scale benchmark dataset designed for real-world face forgery detection. It comprises 60,000 videos with a total of 17.6 million frames, making it significantly larger than existing datasets. The dataset incorporates extensive real-world perturbations, such as transmission errors and compression artifacts, to enhance its complexity and diversity. Fake videos are generated using an end-to-end face swapping framework (DF-VAE), ensuring high quality. DeeperForensics-1.0 includes a hidden test set with highly deceptive manipulated videos, challenging detection algorithms. It facilitates comprehensive evaluation of face forgery detection methods under diverse and realistic conditions, serving as a critical resource for advancing research in this field.
DeeperForensics-1.
Explore all tools that specialize in performance evaluation. This domain focus ensures DeeperForensics-1.0 delivers optimized results for this specific requirement.
Explore all tools that specialize in face swap detection. This domain focus ensures DeeperForensics-1.0 delivers optimized results for this specific requirement.
Explore all tools that specialize in face forgery creation. This domain focus ensures DeeperForensics-1.0 delivers optimized results for this specific requirement.
Comprises 60,000 videos with 17.6 million frames, providing extensive training data.
Includes 7 types of distortions (transmission errors, compression, etc.) at 5 intensity levels.
Fake videos generated by DeepFake Variational Auto-Encoder (DF-VAE).
Contains manipulated videos achieving high deceptive scores in human evaluations.
Released code to implement diverse perturbations used in the dataset.
Download the DeeperForensics-1.0 dataset from the provided link.
Read the dataset documentation for details on the data structure and format.
Install necessary libraries and dependencies (e.g., TensorFlow, PyTorch).
Implement or select a face forgery detection model.
Train the model using the training set of DeeperForensics-1.0.
Evaluate the model's performance on the validation and test sets.
Analyze the results and fine-tune the model for improved accuracy.
All Set
Ready to go
Verified feedback from other users.
"DeeperForensics-1.0 is a highly regarded dataset for its scale and realism, enabling significant advances in face forgery detection research."
Post questions, share tips, and help other users.
No direct alternatives found in this category.