This repository serves as a curated list of research papers, code, and datasets focused on image forgery detection and localization. It aims to provide a comprehensive resource for researchers and practitioners in the field of digital forensics, particularly those working with deep learning techniques for identifying manipulated images.

How It Works

The project meticulously categorizes papers by the type of image manipulation (e.g., splicing, copy-move, inpainting, face forgery) and by publication year. Each entry typically includes links to the paper, official code repositories, datasets, and other relevant resources, often with CCF ranking indicators for conference/journal quality.

Quick Start & Requirements

This repository is a curated list and does not have direct installation or execution requirements. Users can browse the categorized links to access external resources, which may have their own specific software and hardware dependencies (e.g., Python, PyTorch, TensorFlow, specific GPUs).

Highlighted Details

• Extensive coverage of image manipulation types, including splicing, copy-move, inpainting, face forgery, and text tampering.
• Categorization by publication year and CCF ranking, aiding in identifying seminal and high-impact research.
• Direct links to papers, code repositories (often GitHub), datasets, and project pages for easy access to implementations and data.
• Includes emerging areas like AI-generated image detection and the application of Large Multimodal Models (LMMs) in forensics.

Maintenance & Community

The repository is maintained by greatzh. Updates are indicated by "❗Updated" tags, suggesting ongoing curation. Specific community links (e.g., Discord, Slack) are not provided in the README.

Licensing & Compatibility

The repository itself is a list of links and does not impose its own license. The licensing of linked papers and code repositories will vary and must be checked individually. Compatibility for commercial use or closed-source linking depends entirely on the licenses of the linked external resources.

Limitations & Caveats

The repository is a curated list and does not provide any executable code or models directly. Users must navigate to external links for actual implementations, which may have varying levels of documentation, maintenance, and usability. The "CCF rankings" are a subjective measure of academic prestige and not a direct indicator of a paper's practical utility or ease of implementation.