OmniCamera: A Unified Framework for Multi-task Video Generation with Arbitrary Camera Control

TL;DR

OmniCamera is a unified framework that disentangles scene content and camera motion, enabling flexible, independent control over video generation with high visual quality.

Contribution

It introduces a novel hybrid dataset and a dual-level curriculum co-training strategy to improve multi-task video generation with arbitrary camera control.

Findings

Achieves state-of-the-art performance in flexible camera control.

Maintains high visual quality in generated videos.

Successfully disentangles content and camera motion for independent manipulation.

Abstract

Video fundamentally intertwines two crucial axes: the dynamic content of a scene and the camera motion through which it is observed. However, existing generation models often entangle these factors, limiting independent control. In this work, we introduce OmniCamera, a unified framework designed to explicitly disentangle and command these two dimensions. This compositional approach enables flexible video generation by allowing arbitrary pairings of camera and content conditions, unlocking unprecedented creative control. To overcome the fundamental challenges of modality conflict and data scarcity inherent in such a system, we present two key innovations. First, we construct OmniCAM, a novel hybrid dataset combining curated real-world videos with synthetic data that provides diverse paired examples for robust multi-task learning. Second, we propose a Dual-level Curriculum Co-Training strategy that mitigates modality interference and synergistically learns from diverse data sources. This strategy operates on two levels: first, it progressively introduces control modalities by difficulties (condition-level), and second, trains for precise control on synthetic data before adapting to real data for photorealism (data-level). As a result, OmniCamera achieves state-of-the-art performance, enabling flexible control for complex camera movements while maintaining superior visual quality.