You're currently viewing an old version of this dataset. To see the current version, click here.

ControlVideo

ControlVideo is a general framework to utilize T2I diffusion models for one-shot video editing, which incorporates additional conditions such as edge maps, the key frame and temporal attention to improve faithfulness and temporal consistency.

Data and Resources

Cite this as

Min Zhao, Fan Bao, Chongxuan Li, Jun Zhu (2024). Dataset: ControlVideo. https://doi.org/10.57702/4wsbyd1g

DOI retrieved: December 2, 2024

Additional Info

Field Value
Created December 2, 2024
Last update December 2, 2024
Author Min Zhao
More Authors
Fan Bao
Chongxuan Li
Jun Zhu