SceneComposer: Any-Level Semantic Image Synthesis

A new framework for conditional image synthesis from semantic layouts of any precision levels, ranging from pure text to a 2D semantic canvas with precise shapes.

Data and Resources

Cite this as

Yu Zeng1, Zhe Lin2, Jianming Zhang2, Qing Liu2, John Collomosse2, Jason Kuen2, Vishal M. Patel1 (2024). Dataset: SceneComposer: Any-Level Semantic Image Synthesis. https://doi.org/10.57702/7kv69m9c

DOI retrieved: December 2, 2024

Additional Info

Field Value
Created December 2, 2024
Last update December 2, 2024
Author Yu Zeng1
More Authors
Zhe Lin2
Jianming Zhang2
Qing Liu2
John Collomosse2
Jason Kuen2
Vishal M. Patel1
Homepage https://zengxianyu.github.io/scenec/