Abstract
AbstractLarge-scale datasets have played indispensable roles in the recent success of face generation/editing and significantly facilitated the advances of emerging research fields. However, the academic community still lacks a video dataset with diverse facial attribute annotations, which is crucial for the research on face-related videos. In this work, we propose a large-scale, high-quality, and diverse video dataset with rich facial attribute annotations, named the High-Quality Celebrity Video Dataset (CelebV-HQ). CelebV-HQ contains 35, 666 video clips with the resolution of \(512\times 512\) at least, involving 15, 653 identities. All clips are labeled manually with 83 facial attributes, covering appearance, action, and emotion. We conduct a comprehensive analysis in terms of age, ethnicity, brightness stability, motion smoothness, head pose diversity, and data quality to demonstrate the diversity and temporal coherence of CelebV-HQ. Besides, its versatility and potential are validated on two representative tasks, i.e., unconditional video generation and video facial attribute editing. We finally envision the future potential of CelebV-HQ, as well as the new opportunities and challenges it would bring to related research directions. Data, code, and models are publicly available (Project page: https://celebv-hq.github.io/ Code and models: https://github.com/CelebV-HQ/CelebV-HQ). KeywordsLarge-scale video datasetFacial attribute annotationFace video generation and editing
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have