FilmBench: A Film-Grade Benchmark for Cinematic Video Generation
- Published
- Source
- arXiv
- Paper number
- 729
- Field
- Computer Vision
- arXiv ID
- 2607.24241
Key points
- It constructed 1,169 prompts reverse-engineered by professional directors from scenes in award-winning films, of which 1,056 are multi-shot.
- It evaluates cinematographic language along 3 axes, 12 elements, 35 detailed metrics for T2V, and 3 metrics specific to R2V.
- The FilmOps automatic evaluator reproduced human rankings of 9 T2V and 7 R2V models with Spearman correlations of 0.95 and 0.96, respectively.
- It enables comparison of dynamic aesthetics and multi-shot continuity, which existing web-video-centered evaluations miss, against filmmaking standards.
- However, because the benchmark is tailored to film and professional video production, it does not directly represent performance on short vertical videos or general user-generated videos.
Paper links
External research summaries. These are not HDATF publications or measured product results.