Papers › CelebV-HQ: A Large-Scale Video Facial Attributes Dataset

CelebV-HQ: A Large-Scale Video Facial Attributes Dataset

25 Jul 2022arXiv:2207.12393archive 2025-07-28

Hao Zhu, Wayne Wu, Wentao Zhu, Liming Jiang, Siwei Tang, Li Zhang, Ziwei Liu, Chen Change Loy

Large-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 512x512 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. Furthermore, we 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.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

celebv-hq/celebv-hq officialmentioned in papermentioned on GitHub report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

AttributeDiversityFace GenerationUnconditional Video GenerationVideo Generation

Datasets

Introduced by this paper, per the archive.

CelebV-HQ

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Unconditional Video Generation CelebV-HQ StyleGAN-V FID 17.95 #1 of 4 Archive leaderboard report
Unconditional Video Generation CelebV-HQ StyleGAN-V FVD 69.17 #1 of 4 Archive leaderboard report
Unconditional Video Generation CelebV-HQ DIGAN FID 19.39 #2 of 4 Archive leaderboard report
Unconditional Video Generation CelebV-HQ DIGAN FVD 72.98 #2 of 4 Archive leaderboard report
Unconditional Video Generation CelebV-HQ VideoGPT FID 52.95 #3 of 4 Archive leaderboard report
Unconditional Video Generation CelebV-HQ VideoGPT FVD 177.89 #3 of 4 Archive leaderboard report
Unconditional Video Generation CelebV-HQ MoCoGAN-HD FID 21.55 #4 of 4 Archive leaderboard report
Unconditional Video Generation CelebV-HQ MoCoGAN-HD FVD 212.41 #4 of 4 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections