CameraSquad: Achieving content consistency in parallel multi-trajectory camera-controlled video generation

Xu, Zhufeng, Gao, Xuan, Deng, Bailin ORCID: https://orcid.org/0000-0002-0158-7670, Ding, Yikang, Liu, Xiaoqiang, Zhang, Haoxian, Wan, Pengfei, Fu, Hongbo and Gao, Lin 2026. CameraSquad: Achieving content consistency in parallel multi-trajectory camera-controlled video generation. Presented at: SIGGRAPH 2026, Los Angeles, CA, USA, 19-23 July 2026. SIGGRAPH Conference Papers '26: Proceedings of the Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers. ACM, pp. 1-12. 10.1145/3799902.3811048

PDF - Published Version Available under License Creative Commons Attribution Non-commercial No Derivatives. Download (57MB)

Abstract

Camera-controlled video generation is valuable for applications ranging from visual design to providing 2D supervision for 4D generation tasks. However, existing approaches are limited to single-trajectory generation, forcing users to process multiple trajectories in separate batches. This serial inference introduces content inconsistencies across viewpoints due to the inherent randomness of diffusion models. Explicit point cloud methods can only partially address this problem, as single-viewpoint back-projection suffers from sparsity and depth estimation errors. We propose CameraSquad, a multi-trajectory camera control framework that supports both single-trajectory and parallel multi-trajectory generation. Our method achieves precise camera control while preserving input video content through decoupled content and camera control mechanisms. To ensure viewpoint consistency in multi-trajectory mode, we design a dual-mode cross-view attention mechanism that maintains consistency across parallel trajectories while guaranteeing camera control precision. Extensive experiments demonstrate that CameraSquad achieves competitive performance in camera control accuracy, consistency maintenance, and generation quality compared to existing approaches. Our project page is available at https://rabberk.github.io/CameraSquad/.

Item Type:	Conference or Workshop Item - published (Paper)
Date Type:	Publication
Status:	Published
Schools:	Schools > Computer Science & Informatics
Publisher:	ACM
ISBN:	9798400725548
Date of First Compliant Deposit:	20 July 2026
Date of Acceptance:	22 April 2026
Last Modified:	20 Jul 2026 09:00
URI:	https://orca.cardiff.ac.uk/id/eprint/188298

Actions (repository staff only)

Edit Item