Presentation

<
CameraSquad: Achieving Content Consistency in Parallel Multi-Trajectory Camera-Controlled Video Generation
SessionVideo Gen & Camera Control
DescriptionCameraSquad is a multi-trajectory camera control framework that supports both single-trajectory and parallel multi-trajectory video generation. By decoupling content and camera control mechanisms and using a dual-mode cross-view attention mechanism, it ensures viewpoint consistency and camera control precision in multi-trajectory mode.
Authors
Zhufeng Xu
Institute of Computing Technology, Chinese Academy of Sciences
University of Chinese Academy of Sciences
Xuan Gao
Institute of Computing Technology, Chinese Academy of Sciences
University of Chinese Academy of Sciences
Bailin Deng
School of Computer Science and Informatics, Cardiff University
Yikang Ding
Kling Team, Kuaishou Technology
Xiaoqiang Liu
Kling Team, Kuaishou Technology
Haoxian Zhang
Kling Team, Kuaishou Technology
Pengfei Wan
Kling Team, Kuaishou Technology
Hongbo Fu
The Hong Kong University of Science and Technology
Lin Gao
Institute of Computing Technology, Chinese Academy of Sciences
University of Chinese Academy of Sciences
Event Type
Technical Paper
TimeTuesday, 21 July 20269:50am - 10:00am PDT
LocationRoom 408 B
Digital Library PDF
Session Time & Location
Sunday, 19 July 20266:00pm - 8:45pm PDTHall K
Tuesday, 21 July 20269:00am - 10:30am PDTRoom 408 B
Keywords
Artificial Intelligence/Machine Learning
Generative AI
Registration Categories
Full Conference Supporter
Full Conference
Next PresentationNext PresentationVideo Gen & Camera Control - Interactive Discussion
Similar Presentations
ViewWeaver: Geometry-Grounded Generative Rendering for 3D-Aware Image Customization
MV-S2V: Multi-View Subject-Consistent Video Generation
ReRoPE: Repurposing RoPE for Relative Camera Control