A benchmark dataset for identity-consistent human face image generation quality assessment. It was created by author aleizb and last updated on 2026-05-26. The dataset is intended to support fair algorithmic comparisons in virtual reality, film production, digital avatars, and personalized entertainment.
Use Cases
- Benchmarking generative model performance based on identity-consistent face generation quality.
- Developing quality assessment algorithms based on the dual-dimension evaluation framework.
- Training evaluation metrics for tasks in virtual reality and digital avatar creation.
Strengths
- Specifically designed for the core task of identity-consistent face generation.
- Provides a dual-dimension quality assessment framework as described.
- Last updated on 2026-05-26, indicating recent maintenance.
Limitations
- Description metadata is limited; actual data quality requires manual inspection after download.
- Column-level documentation is absent; field semantics must be inferred after download.
- Row count and file formats are unknown, which may limit suitability assessment.
Provenance
- Source
- huggingface
- Freshness
- 2026-05-26 05:46:28