Research map / Video / Video generation
Better Call CineCrew: Consistent Ultra-Long Narrative-to-Film Generation
Jiaben Chen, Sixun Dong, Qinhong Zhou, Raine Ma, Zhiyang Dou, Wojciech Matusik, Chuang Gan
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add FilmDSL structured intermediate (ablation) | CineCrew · CineCrewEval ablation (20 MovieBench narratives) | Beat Readability: 3.05 -> 4.90 | Improved |
| add FilmDSL structured intermediate (ablation) | CineCrew · CineCrewEval ablation (20 MovieBench narratives) | Narrative Coherence: 3.45 -> 4.70 | Improved |
| add Assets Memory (character sheets, set assets) (ablation) | CineCrew · CineCrewEval ablation (20 MovieBench narratives) | Identity Consistency: 61.29 -> 75.12 | Improved |
| add Assets Memory (ablation) | CineCrew · CineCrewEval ablation (20 MovieBench narratives) | Persona Alignment: 3.50 -> 4.75 | Improved |
| add Showrunner (global meta) (ablation) | CineCrew · CineCrewEval ablation (20 MovieBench narratives) | Prop Permanence: 70.15 -> 78.59 | Improved |
| add Showrunner (ablation) | CineCrew · CineCrewEval ablation (20 MovieBench narratives) | Identity Consistency: 67.82 -> 75.12 | Improved |
| add Dailies Reviewer (closed-loop refinement) (ablation) | CineCrew · CineCrewEval ablation (20 MovieBench narratives) | Layout Continuity: 3.95 -> 4.50 | Improved |
| add Dailies Reviewer (ablation) | CineCrew · CineCrewEval ablation (20 MovieBench narratives) | Prop Permanence: 70.24 -> 78.59 | Improved |
| add Dailies Reviewer (ablation) | CineCrew · CineCrewEval ablation (20 MovieBench narratives) | Persona Alignment: 4.75 -> 4.75 | No clear effect |
| add Production Rulebook (ablation) | CineCrew · CineCrewEval ablation (20 MovieBench narratives) | Identity Consistency: 73.78 -> 75.12 | Improved |
| add Production Rulebook (ablation) | CineCrew · CineCrewEval ablation (20 MovieBench narratives) | Cross Coherence: 4.55 -> 4.65 | Improved |
| add Production Rulebook (ablation) | CineCrew · CineCrewEval ablation (20 MovieBench narratives) | Cinematic Look: 4.80 -> 4.85 | No clear effect |
Closest papers by meaning
- MovieDreamer: Hierarchical Generation for Coherent Long Visual Sequences (ICLR 2025 · similarity 0.88)
- Stable Cinemetrics : Structured Taxonomy and Evaluation for Professional Video Generation (NeurIPS 2025 · similarity 0.88)
- SceneDecorator: Towards Scene-Oriented Story Generation with Scene Planning and Scene Consistency (NeurIPS 2025 · similarity 0.87)
- Auteur: Language-Driven Cinematographic Framing for Human-Centric Video Generation (NeurIPS 2026 · similarity 0.86)
- Narrative Weaver: Towards Controllable Long-Range Visual Consistency with Multi-Modal Conditioning (CVPR 2026 · similarity 0.86)
- CineTechBench: A Benchmark for Cinematographic Technique Understanding and Generation (NeurIPS 2025 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
