CamCloneMaster: Enabling Reference-based Camera Control for Video Generation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Luo, Yawen, Bai, Jianhong, Shi, Xiaoyu, Xia, Menghan, Wang, Xintao, Wan, Pengfei, Zhang, Di, Gai, Kun, Xue, Tianfan
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916776237858816
author Luo, Yawen
Bai, Jianhong
Shi, Xiaoyu
Xia, Menghan
Wang, Xintao
Wan, Pengfei
Zhang, Di
Gai, Kun
Xue, Tianfan
author_facet Luo, Yawen
Bai, Jianhong
Shi, Xiaoyu
Xia, Menghan
Wang, Xintao
Wan, Pengfei
Zhang, Di
Gai, Kun
Xue, Tianfan
contents Camera control is crucial for generating expressive and cinematic videos. Existing methods rely on explicit sequences of camera parameters as control conditions, which can be cumbersome for users to construct, particularly for intricate camera movements. To provide a more intuitive camera control method, we propose CamCloneMaster, a framework that enables users to replicate camera movements from reference videos without requiring camera parameters or test-time fine-tuning. CamCloneMaster seamlessly supports reference-based camera control for both Image-to-Video and Video-to-Video tasks within a unified framework. Furthermore, we present the Camera Clone Dataset, a large-scale synthetic dataset designed for camera clone learning, encompassing diverse scenes, subjects, and camera movements. Extensive experiments and user studies demonstrate that CamCloneMaster outperforms existing methods in terms of both camera controllability and visual quality.
format Preprint
id arxiv_https___arxiv_org_abs_2506_03140
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle CamCloneMaster: Enabling Reference-based Camera Control for Video Generation
Luo, Yawen
Bai, Jianhong
Shi, Xiaoyu
Xia, Menghan
Wang, Xintao
Wan, Pengfei
Zhang, Di
Gai, Kun
Xue, Tianfan
Computer Vision and Pattern Recognition
Camera control is crucial for generating expressive and cinematic videos. Existing methods rely on explicit sequences of camera parameters as control conditions, which can be cumbersome for users to construct, particularly for intricate camera movements. To provide a more intuitive camera control method, we propose CamCloneMaster, a framework that enables users to replicate camera movements from reference videos without requiring camera parameters or test-time fine-tuning. CamCloneMaster seamlessly supports reference-based camera control for both Image-to-Video and Video-to-Video tasks within a unified framework. Furthermore, we present the Camera Clone Dataset, a large-scale synthetic dataset designed for camera clone learning, encompassing diverse scenes, subjects, and camera movements. Extensive experiments and user studies demonstrate that CamCloneMaster outperforms existing methods in terms of both camera controllability and visual quality.
title CamCloneMaster: Enabling Reference-based Camera Control for Video Generation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2506.03140