This repository is a curated list of academic papers and code related to face forgery generation and detection, primarily targeting researchers and practitioners in computer vision and AI security. It serves as a comprehensive resource for understanding the state-of-the-art techniques in creating and identifying manipulated facial imagery and videos.

How It Works

The repository organizes a vast collection of research papers, categorized by the type of face manipulation (e.g., face swap, attribute manipulation, expression reenactment) and detection methods (e.g., spatial clues, temporal clues, audio+clues, generalizable detection). It links to associated code repositories and survey papers, providing a structured overview of the field.

Quick Start & Requirements

This is a curated list, not a runnable software package. No installation or execution commands are applicable.

Highlighted Details

• Extensive categorization of face forgery generation and detection techniques.
• Links to numerous research papers with associated code repositories.
• Includes a comprehensive list of relevant datasets for benchmarking.
• Covers various detection strategies, including spatial, temporal, audio, and generalizable approaches.

Maintenance & Community

The repository is maintained by clpeng, with an invitation for contributions via pull requests or email.

Licensing & Compatibility

The repository itself is a list and does not have a specific license. The linked code repositories and papers will have their own respective licenses.

Limitations & Caveats

As a curated list, it does not provide any executable functionality or pre-trained models. The utility of the repository depends entirely on the user's ability to access and utilize the linked research papers and code.