Research map / Video / Video generation
HoloCine: Holistic Generation of Cinematic Multi-Shot Long Video Narratives
Yihao Meng, Hao Ouyang, Yue Yu, Qiuyu Wang, Wen Wang, Ka Leong Cheng, Hanlin Wang, Shuailei Ma, Yixuan Li, Cheng Chen, Yanhong Zeng, Xing Zhu and 2 more
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 window cross-attention (ablation) | HoloCine (Wan2.2 5B) · Multi-shot ablation benchmark | Transition Control (SCA): 0.6266 -> 0.9736 | Improved |
| add window cross-attention (ablation) | HoloCine (Wan2.2 5B) · Multi-shot ablation benchmark | Semantic Consistency: 0.1562 -> 0.1739 | Improved |
| add window cross-attention (ablation) | HoloCine (Wan2.2 5B) · Multi-shot ablation benchmark | Inter-shot Consistency: 0.7009 -> 0.7225 | Improved |
| add window cross-attention (ablation) | HoloCine (Wan2.2 5B) · Multi-shot ablation benchmark | Aesthetic Quality: 0.5755 -> 0.5693 | No clear effect |
| add inter-shot summary tokens (ablation) | HoloCine (Wan2.2 5B) · Multi-shot ablation benchmark | Inter-shot Consistency: 0.6761 -> 0.7225 | Improved |
| add inter-shot summary tokens (ablation) | HoloCine (Wan2.2 5B) · Multi-shot ablation benchmark | Semantic Consistency: 0.1642 -> 0.1739 | Improved |
| add inter-shot summary tokens (ablation) | HoloCine (Wan2.2 5B) · Multi-shot ablation benchmark | Transition Control (SCA): 0.9675 -> 0.9736 | Improved |
| use sparse inter-shot attention instead of full attention (ablation) | HoloCine (Wan2.2 5B) · Multi-shot ablation benchmark | Inter-shot Consistency: 0.7231 -> 0.7225 | No clear effect |
| use sparse inter-shot attention instead of full attention (ablation) | HoloCine (Wan2.2 5B) · Multi-shot ablation benchmark | Transition Control (SCA): 0.8923 -> 0.9736 | Improved |
| use sparse inter-shot attention instead of full attention (ablation) | HoloCine (Wan2.2 5B) · Multi-shot ablation benchmark | Semantic Consistency: 0.1738 -> 0.1739 | No clear effect |
| holistic multi-shot fine-tuning of Wan2.2 14B | HoloCine · Multi-shot benchmark (100 prompts) | Transition Control (SCA): 0.4843 -> 0.9837 | Improved |
| holistic multi-shot fine-tuning of Wan2.2 14B | HoloCine · Multi-shot benchmark (100 prompts) | Inter-shot Consistency: 0.6772 -> 0.7509 | Improved |
Later papers that compared with this method
1 later accepted paper reports HoloCine as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- EntityBench: Towards Entity-Consistent Long-Range Multi-Shot Video Generation (NeurIPS 2026 · better on 8 of 9 shared results)
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- MovieDreamer: Hierarchical Generation for Coherent Long Visual Sequences (ICLR 2025 · similarity 0.87)
- CineTechBench: A Benchmark for Cinematographic Technique Understanding and Generation (NeurIPS 2025 · similarity 0.87)
- SceneDecorator: Towards Scene-Oriented Story Generation with Scene Planning and Scene Consistency (NeurIPS 2025 · similarity 0.86)
- Auteur: Language-Driven Cinematographic Framing for Human-Centric Video Generation (NeurIPS 2026 · similarity 0.86)
- StoryDiffusion: Consistent Self-Attention for Long-Range Image and Video Generation (NeurIPS 2024 · similarity 0.86)
- CineOrchestra: Unified Entity-Centric Conditioning for Cinematic Video Generation (NeurIPS 2026 · 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.
