I2VControl-Camera: Precise Video Camera Control with Adjustable Motion Strength

TL;DR

This paper introduces I2VControl-Camera, a new method for precise and adjustable video camera control that models higher-order motion components to enhance controllability and realism in video generation.

Contribution

It proposes a novel control framework using point trajectories and higher-order motion modeling, with an adapter architecture for improved camera control in video synthesis.

Findings

Outperforms previous methods quantitatively and qualitatively

Enhances control precision and motion adjustability

Effective in static and dynamic scenes

Abstract

Video generation technologies are developing rapidly and have broad potential applications. Among these technologies, camera control is crucial for generating professional-quality videos that accurately meet user expectations. However, existing camera control methods still suffer from several limitations, including control precision and the neglect of the control for subject motion dynamics. In this work, we propose I2VControl-Camera, a novel camera control method that significantly enhances controllability while providing adjustability over the strength of subject motion. To improve control precision, we employ point trajectory in the camera coordinate system instead of only extrinsic matrix information as our control signal. To accurately control and adjust the strength of subject motion, we explicitly model the higher-order components of the video trajectory expansion, not merely the linear terms, and design an operator that effectively represents the motion strength. We use an adapter architecture that is independent of the base model structure. Experiments on static and dynamic scenes show that our framework outperformances previous methods both quantitatively and qualitatively. The project page is: https://wanquanf.github.io/I2VControlCamera .