Diffusion-Based Scene Graph to Image Generation with Masked Contrastive Pre-Training

Generating images from graph-structured inputs, such as scene graphs, is uniquely challenging due to the difficulty of aligning nodes and connections in graphs with objects and their relations in images.

Data and Resources

Cite this as

Ling Yang, Zhilin Huang, Yang Song, Shenda Hong, Guohao Li, Wentao Zhang, Bin Cui, Ming-Hsuan Yang (2024). Dataset: Diffusion-Based Scene Graph to Image Generation with Masked Contrastive Pre-Training. https://doi.org/10.57702/mbyw8qyh

DOI retrieved: December 16, 2024

Additional Info

Field Value
Created December 16, 2024
Last update December 16, 2024
Author Ling Yang
More Authors
Zhilin Huang
Yang Song
Shenda Hong
Guohao Li
Wentao Zhang
Bin Cui
Ming-Hsuan Yang
Homepage https://github.com/YangLing0818/SGDiff