VividCam: Learning Unconventional Camera Motions from Virtual Synthetic Videos

arXiv:2510.24904 · cs.CV · Submitted 2025-10-28 · Read on arXiv

cs.CV

Submitted: 2025-10-28

Updated: 2026-09-21

Comments: Published in ICML 2026. 22 pages, 9 figures

Project page: https://wuqiuche.github.io/VividCamDemoPage

License: http://creativecommons.org/licenses/by-nc-sa/4.0/

The gist: Although recent video generative models are getting more capable of following external camera controls, imposed by either text descriptions or camera trajectories, they still struggle to generalize

Terminology

Abstract

Although recent video generative models are getting more capable of following external camera controls, imposed by either text descriptions or camera trajectories, they still struggle to generalize to unconventional camera motions, which is crucial in creating truly original and artistic videos. The challenge lies in finding sufficient training videos with the intended uncommon camera motions. To this end, we propose VividCam, a training paradigm that enables diffusion models to learn complex camera motions from synthetic videos, releasing the reliance on collecting realistic training videos. VividCam incorporates multiple disentanglement strategies that isolate camera motion learning from synthetic appearance artifacts, ensuring more robust motion representation and mitigating domain shift. We show that our design synthesizes a wide range of precisely controlled camera motions using surprisingly simple synthetic data. Notably, this synthetic data often consists of basic geometries within a low-poly 3D scene and can be efficiently rendered by engines like Unity. Our video results can be found in https://wuqiuche.github.io/VividCamDemoPage/ .

Sources

Related papers