STAGE: Storyboard-Anchored Generation for Cinematic Multi-shot Narrative
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914394499186688 |
|---|---|
| author | Zhang, Peixuan Jia, Zijian Liu, Kaiqi Weng, Shuchen Li, Si Shi, Boxin |
| author_facet | Zhang, Peixuan Jia, Zijian Liu, Kaiqi Weng, Shuchen Li, Si Shi, Boxin |
| contents | While recent advancements in generative models have achieved remarkable visual fidelity in video synthesis, creating coherent multi-shot narratives remains a significant challenge. To address this, keyframe-based approaches have emerged as a promising alternative to computationally intensive end-to-end methods, offering the advantages of fine-grained control and greater efficiency. However, these methods often fail to maintain cross-shot consistency and capture cinematic language. In this paper, we introduce STAGE, a SToryboard-Anchored GEneration workflow to reformulate the keyframe-based multi-shot video generation task. Instead of using sparse keyframes, we propose STEP2 to predict a structural storyboard composed of start-end frame pairs for each shot. We introduce the multi-shot memory pack to ensure long-range entity consistency, the dual-encoding strategy for intra-shot coherence, and the two-stage training scheme to learn cinematic inter-shot transition. We also contribute the large-scale ConStoryBoard dataset, including high-quality movie clips with fine-grained annotations for story progression, cinematic attributes, and human preferences. Extensive experiments demonstrate that STAGE achieves superior performance in structured narrative control and cross-shot coherence. Our code will be available at this url. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_12372 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | STAGE: Storyboard-Anchored Generation for Cinematic Multi-shot Narrative Zhang, Peixuan Jia, Zijian Liu, Kaiqi Weng, Shuchen Li, Si Shi, Boxin Computer Vision and Pattern Recognition While recent advancements in generative models have achieved remarkable visual fidelity in video synthesis, creating coherent multi-shot narratives remains a significant challenge. To address this, keyframe-based approaches have emerged as a promising alternative to computationally intensive end-to-end methods, offering the advantages of fine-grained control and greater efficiency. However, these methods often fail to maintain cross-shot consistency and capture cinematic language. In this paper, we introduce STAGE, a SToryboard-Anchored GEneration workflow to reformulate the keyframe-based multi-shot video generation task. Instead of using sparse keyframes, we propose STEP2 to predict a structural storyboard composed of start-end frame pairs for each shot. We introduce the multi-shot memory pack to ensure long-range entity consistency, the dual-encoding strategy for intra-shot coherence, and the two-stage training scheme to learn cinematic inter-shot transition. We also contribute the large-scale ConStoryBoard dataset, including high-quality movie clips with fine-grained annotations for story progression, cinematic attributes, and human preferences. Extensive experiments demonstrate that STAGE achieves superior performance in structured narrative control and cross-shot coherence. Our code will be available at this url. |
| title | STAGE: Storyboard-Anchored Generation for Cinematic Multi-shot Narrative |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2512.12372 |