Generative Photographic Control for Scene-Consistent Video Cinematic Editing

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Sun, Huiqiang, Shen, Liao, Peng, Zhan, Wang, Kun, Wu, Size, Zang, Yuhang, Liu, Tianqi, Huang, Zihao, Zeng, Xingyu, Cao, Zhiguo, Li, Wei, Loy, Chen Change
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866914160453877760
author Sun, Huiqiang
Shen, Liao
Peng, Zhan
Wang, Kun
Wu, Size
Zang, Yuhang
Liu, Tianqi
Huang, Zihao
Zeng, Xingyu
Cao, Zhiguo
Li, Wei
Loy, Chen Change
author_facet Sun, Huiqiang
Shen, Liao
Peng, Zhan
Wang, Kun
Wu, Size
Zang, Yuhang
Liu, Tianqi
Huang, Zihao
Zeng, Xingyu
Cao, Zhiguo
Li, Wei
Loy, Chen Change
contents Cinematic storytelling is profoundly shaped by the artful manipulation of photographic elements such as depth of field and exposure. These effects are crucial in conveying mood and creating aesthetic appeal. However, controlling these effects in generative video models remains highly challenging, as most existing methods are restricted to camera motion control. In this paper, we propose CineCtrl, the first video cinematic editing framework that provides fine control over professional camera parameters (e.g., bokeh, shutter speed). We introduce a decoupled cross-attention mechanism to disentangle camera motion from photographic inputs, allowing fine-grained, independent control without compromising scene consistency. To overcome the shortage of training data, we develop a comprehensive data generation strategy that leverages simulated photographic effects with a dedicated real-world collection pipeline, enabling the construction of a large-scale dataset for robust model training. Extensive experiments demonstrate that our model generates high-fidelity videos with precisely controlled, user-specified photographic camera effects.
format Preprint
id arxiv_https___arxiv_org_abs_2511_12921
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Generative Photographic Control for Scene-Consistent Video Cinematic Editing
Sun, Huiqiang
Shen, Liao
Peng, Zhan
Wang, Kun
Wu, Size
Zang, Yuhang
Liu, Tianqi
Huang, Zihao
Zeng, Xingyu
Cao, Zhiguo
Li, Wei
Loy, Chen Change
Computer Vision and Pattern Recognition
Cinematic storytelling is profoundly shaped by the artful manipulation of photographic elements such as depth of field and exposure. These effects are crucial in conveying mood and creating aesthetic appeal. However, controlling these effects in generative video models remains highly challenging, as most existing methods are restricted to camera motion control. In this paper, we propose CineCtrl, the first video cinematic editing framework that provides fine control over professional camera parameters (e.g., bokeh, shutter speed). We introduce a decoupled cross-attention mechanism to disentangle camera motion from photographic inputs, allowing fine-grained, independent control without compromising scene consistency. To overcome the shortage of training data, we develop a comprehensive data generation strategy that leverages simulated photographic effects with a dedicated real-world collection pipeline, enabling the construction of a large-scale dataset for robust model training. Extensive experiments demonstrate that our model generates high-fidelity videos with precisely controlled, user-specified photographic camera effects.
title Generative Photographic Control for Scene-Consistent Video Cinematic Editing
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2511.12921