VASE

The VASE dataset is used for video object-centric appearance and shape edits. It consists of 30 videos from the DAVIS dataset, with 3 driver images to edit each video.

Data and Resources

Cite this as

Elia Peruzzo, Vidit Goel, Dejia Xu, Xingqian Xu, Yifan Jiang, Zhangyang Wang, Humphrey Shi, Nicu Sebe (2024). Dataset: VASE. https://doi.org/10.57702/52kpov41

DOI retrieved: December 16, 2024

Additional Info

Field Value
Created December 16, 2024
Last update December 16, 2024
Defined In https://doi.org/10.48550/arXiv.2401.02473
Author Elia Peruzzo
More Authors
Vidit Goel
Dejia Xu
Xingqian Xu
Yifan Jiang
Zhangyang Wang
Humphrey Shi
Nicu Sebe