Probing into Camera Control of Video Models

TL;DR

This paper introduces a geometric approach to camera control in video models, reformulating it as displacement fields, enabling effective control without retraining and revealing biases in existing models.

Contribution

It proposes a novel geometric guidance method for camera control in video diffusion models that requires no additional training and serves as a probe for model capabilities.

Findings

Effective camera control achieved with minimal quality degradation.

Identified universal biases shared by video models.

Benchmarking reveals disparities in multi-view generation performance.

Abstract

Video is a rich and scalable source of 3D/4D visual observations, and camera control is a key capability for video generation models to produce geometrically meaningful content. Existing approaches typically learn a mapping from camera motion to video using additional camera modules and paired data. However, such datasets are often limited in scale, diversity, and scene dynamics, which can bias the model toward a narrow output distribution and compromise the strong prior learned by the base model. These limitations motivate a different perspective on camera control. In this paper, we show that camera control need not be modeled as an implicit mapping problem, but can instead be treated as a form of geometric guidance that induces displacements across frames. Specifically, we reformulate camera control into a set of displacement fields and apply them via differentiable resampling of latent features during denoising. Our simple approach achieves effective camera control with minimal degradation across diverse quality metrics compared to fine-tuned baselines. Since our method is applicable to most video diffusion models without training, it can also serve as a probe to study the camera control capabilities of base models. Using this probe, we identify universal biases shared by representative video models, as well as disparities in their responses to camera control. Finally, we benchmark their performance in multi-view generation, offering insights into their potential for 3D/4D tasks.