OmniCam: Unified Multimodal Video Generation via Camera Control

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Yang, Xiaoda, Xu, Jiayang, Luan, Kaixuan, Zhan, Xinyu, Qiu, Hongshun, Shi, Shijun, Li, Hao, Yang, Shuai, Zhang, Li, Yu, Checheng, Lu, Cewu, Yang, Lixin
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866908299071324160
author Yang, Xiaoda
Xu, Jiayang
Luan, Kaixuan
Zhan, Xinyu
Qiu, Hongshun
Shi, Shijun
Li, Hao
Yang, Shuai
Zhang, Li
Yu, Checheng
Lu, Cewu
Yang, Lixin
author_facet Yang, Xiaoda
Xu, Jiayang
Luan, Kaixuan
Zhan, Xinyu
Qiu, Hongshun
Shi, Shijun
Li, Hao
Yang, Shuai
Zhang, Li
Yu, Checheng
Lu, Cewu
Yang, Lixin
contents Camera control, which achieves diverse visual effects by changing camera position and pose, has attracted widespread attention. However, existing methods face challenges such as complex interaction and limited control capabilities. To address these issues, we present OmniCam, a unified multimodal camera control framework. Leveraging large language models and video diffusion models, OmniCam generates spatio-temporally consistent videos. It supports various combinations of input modalities: the user can provide text or video with expected trajectory as camera path guidance, and image or video as content reference, enabling precise control over camera motion. To facilitate the training of OmniCam, we introduce the OmniTr dataset, which contains a large collection of high-quality long-sequence trajectories, videos, and corresponding descriptions. Experimental results demonstrate that our model achieves state-of-the-art performance in high-quality camera-controlled video generation across various metrics.
format Preprint
id arxiv_https___arxiv_org_abs_2504_02312
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle OmniCam: Unified Multimodal Video Generation via Camera Control
Yang, Xiaoda
Xu, Jiayang
Luan, Kaixuan
Zhan, Xinyu
Qiu, Hongshun
Shi, Shijun
Li, Hao
Yang, Shuai
Zhang, Li
Yu, Checheng
Lu, Cewu
Yang, Lixin
Computer Vision and Pattern Recognition
Artificial Intelligence
Camera control, which achieves diverse visual effects by changing camera position and pose, has attracted widespread attention. However, existing methods face challenges such as complex interaction and limited control capabilities. To address these issues, we present OmniCam, a unified multimodal camera control framework. Leveraging large language models and video diffusion models, OmniCam generates spatio-temporally consistent videos. It supports various combinations of input modalities: the user can provide text or video with expected trajectory as camera path guidance, and image or video as content reference, enabling precise control over camera motion. To facilitate the training of OmniCam, we introduce the OmniTr dataset, which contains a large collection of high-quality long-sequence trajectories, videos, and corresponding descriptions. Experimental results demonstrate that our model achieves state-of-the-art performance in high-quality camera-controlled video generation across various metrics.
title OmniCam: Unified Multimodal Video Generation via Camera Control
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2504.02312