This repository is a curated list of resources, including papers, code, and datasets, focused on "talking face" or "talking head" generation. It serves researchers and practitioners in the field of AI-driven animation and digital human synthesis, providing a centralized hub for the latest advancements and foundational work.

How It Works

The project acts as a comprehensive bibliography, categorizing research by methodology (e.g., 2D Video, 3D Animation), driving mechanism (audio-driven, text-driven), and specific features (emotion control, person-dependent/independent). It links to papers, code repositories, and project pages, facilitating discovery and access to relevant research.

Quick Start & Requirements

This is a curated list, not a runnable software project. No installation or specific requirements are applicable.

Highlighted Details

• Extensive collection of papers from 2017 to the present, with a significant focus on recent advancements in 2023-2024.
• Categorization includes both 2D and 3D talking face generation, as well as video-driven and audio-driven approaches.
• Links to associated code, project pages, and datasets are provided for many entries.
• Includes a dedicated section for survey papers and relevant benchmark datasets.

Maintenance & Community

The repository is actively maintained, with recent updates in September 2022 and November 2021, and a continuous stream of new papers added, particularly in 2024. Pull requests are welcomed for suggestions, new papers, or corrections.

Licensing & Compatibility

The repository itself is a list of links and does not have a specific software license. The linked resources will have their own respective licenses.

Limitations & Caveats

Access to some linked papers may require academic subscriptions. The project is a living document and its comprehensiveness is dependent on community contributions.