UnitedHuman: Harnessing Multi-Source Data for High-Resolution Human Generation

Human generation has achieved significant progress. Non nonetheless, existing methods still struggle to synthesize specific regions such as faces and hands. We propose to use multi-source datasets with various resolution images to jointly learn a high-resolution human generative model.

Data and Resources

Cite this as

Jianglin Fu, Shikai Li, Yuming Jiang, Kwan-Yee Lin, Wayne Wu, Ziwei Liu (2024). Dataset: UnitedHuman: Harnessing Multi-Source Data for High-Resolution Human Generation. https://doi.org/10.57702/fjk9g9ey

DOI retrieved: December 3, 2024

Additional Info

Field Value
Created December 3, 2024
Last update December 3, 2024
Author Jianglin Fu
More Authors
Shikai Li
Yuming Jiang
Kwan-Yee Lin
Wayne Wu
Ziwei Liu
Homepage https://unitedhuman.github.io/