Research map / Video / Video generation
STAGE: Storyboard-Anchored Generation for Cinematic Multi-shot Narrative
Peixuan Zhang, Zijian Jia, Kaiqi Liu, Shuchen Weng, Si Li, Boxin Shi
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 multi-shot memory pack (ablation) | STAGE · ConStoryBoard test (multi-shot video) | SC-E: 0.6088 -> 0.6917 | Improved |
| add multi-shot memory pack (ablation) | STAGE · ConStoryBoard test (multi-shot video) | BC-E: 0.7311 -> 0.8207 | Improved |
| add multi-shot memory pack (ablation) | STAGE · ConStoryBoard test (multi-shot video) | ISC: 0.5466 -> 0.6985 | Improved |
| add multi-shot memory pack (ablation) | STAGE · ConStoryBoard test (multi-shot video) | TVS: 0.2370 -> 0.2732 | Improved |
| add dual-encoding strategy (ablation) | STAGE · ConStoryBoard test (multi-shot video) | SC: 0.9542 -> 0.9695 | Improved |
| add dual-encoding strategy (ablation) | STAGE · ConStoryBoard test (multi-shot video) | BC: 0.9476 -> 0.9685 | Improved |
| add dual-encoding strategy (ablation) | STAGE · ConStoryBoard test (multi-shot video) | OVQ: 0.7803 -> 0.8929 | Improved |
| add dual-encoding strategy (ablation) | STAGE · ConStoryBoard test (multi-shot video) | SC-E: 0.6803 -> 0.6917 | No clear effect |
| add preference alignment stage (two-stage training) (ablation) | STAGE · ConStoryBoard test (multi-shot video) | TVS: 0.2195 -> 0.2732 | Improved |
| add preference alignment stage (two-stage training) (ablation) | STAGE · ConStoryBoard test (multi-shot video) | STS: 0.5111 -> 0.6255 | Improved |
| add preference alignment stage (two-stage training) (ablation) | STAGE · ConStoryBoard test (multi-shot video) | OC: 0.2635 -> 0.2713 | No clear effect |
| add preference alignment stage (two-stage training) (ablation) | STAGE · ConStoryBoard test (multi-shot video) | SC-E: 0.6636 -> 0.6917 | Improved |
Closest papers by meaning
- MovieDreamer: Hierarchical Generation for Coherent Long Visual Sequences (ICLR 2025 · similarity 0.89)
- EntityBench: Towards Entity-Consistent Long-Range Multi-Shot Video Generation (NeurIPS 2026 · similarity 0.88)
- SceneDecorator: Towards Scene-Oriented Story Generation with Scene Planning and Scene Consistency (NeurIPS 2025 · similarity 0.88)
- Auteur: Language-Driven Cinematographic Framing for Human-Centric Video Generation (NeurIPS 2026 · similarity 0.88)
- MovieBench: A Hierarchical Movie Level Dataset for Long Video Generation (CVPR 2025 · similarity 0.88)
- Storybooth: Training-Free Multi-Subject Consistency for Improved Visual Storytelling (ICLR 2025 · similarity 0.87)
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.
