CineVerse: Consistent Keyframe Synthesis for Cinematic Scene Composition
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912350515232768 |
|---|---|
| author | Phung, Quynh Mai, Long Heilbron, Fabian David Caba Liu, Feng Huang, Jia-Bin Ham, Cusuh |
| author_facet | Phung, Quynh Mai, Long Heilbron, Fabian David Caba Liu, Feng Huang, Jia-Bin Ham, Cusuh |
| contents | We present CineVerse, a novel framework for the task of cinematic scene composition. Similar to traditional multi-shot generation, our task emphasizes the need for consistency and continuity across frames. However, our task also focuses on addressing challenges inherent to filmmaking, such as multiple characters, complex interactions, and visual cinematic effects. In order to learn to generate such content, we first create the CineVerse dataset. We use this dataset to train our proposed two-stage approach. First, we prompt a large language model (LLM) with task-specific instructions to take in a high-level scene description and generate a detailed plan for the overall setting and characters, as well as the individual shots. Then, we fine-tune a text-to-image generation model to synthesize high-quality visual keyframes. Experimental results demonstrate that CineVerse yields promising improvements in generating visually coherent and contextually rich movie scenes, paving the way for further exploration in cinematic video synthesis. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_19894 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | CineVerse: Consistent Keyframe Synthesis for Cinematic Scene Composition Phung, Quynh Mai, Long Heilbron, Fabian David Caba Liu, Feng Huang, Jia-Bin Ham, Cusuh Computer Vision and Pattern Recognition We present CineVerse, a novel framework for the task of cinematic scene composition. Similar to traditional multi-shot generation, our task emphasizes the need for consistency and continuity across frames. However, our task also focuses on addressing challenges inherent to filmmaking, such as multiple characters, complex interactions, and visual cinematic effects. In order to learn to generate such content, we first create the CineVerse dataset. We use this dataset to train our proposed two-stage approach. First, we prompt a large language model (LLM) with task-specific instructions to take in a high-level scene description and generate a detailed plan for the overall setting and characters, as well as the individual shots. Then, we fine-tune a text-to-image generation model to synthesize high-quality visual keyframes. Experimental results demonstrate that CineVerse yields promising improvements in generating visually coherent and contextually rich movie scenes, paving the way for further exploration in cinematic video synthesis. |
| title | CineVerse: Consistent Keyframe Synthesis for Cinematic Scene Composition |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2504.19894 |