- Published on
OmniCam: Unified Multimodal Video Generation via Camera Control
- Authors
- Name
- Xiaoda Yang
- Name
- Jiayang Xu
- Name
- Kaixuan Luan
- Name
- Xinyu Zhan
- Name
- Hongshun Qiu
- Name
- Shijun Shi
- Name
- Hao Li
- Name
- Shuai Yang
- Name
- Li Zhang
- Name
- Checheng Yu
- Name
- Cewu Lu
- Name
- Lixin Yang
- Affiliation
- Zhejiang University
- Affiliation
- Shanghai Jiao Tong University
- Affiliation
- Beijing University of Technology
- Affiliation
- Jiangnan University
- Affiliation
- University of Science and Technology of China
- Affiliation
- Nanjing University
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.