HIDE

A large-scale dataset for human-aware motion deblurring, consisting of 8,422 pairs of blurry and sharp images with 65,784 densely annotated FG human bounding boxes.

Data and Resources

Cite this as

Sidun Liu, Peng Qiao, Yong Dou (2024). Dataset: HIDE. https://doi.org/10.57702/fnjaod1y

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.2001.06816
Citation
  • https://doi.org/10.48550/arXiv.2208.13029
Author Sidun Liu
More Authors
Peng Qiao
Yong Dou
Homepage https://ieeexplore.ieee.org/document/8661118