Break-A-Scene: Extracting Multiple Concepts from a Single Image

The dataset is created by augmenting a single input image with masks that indicate the presence of target concepts. The masks can be provided by the user or generated automatically by a pre-trained segmentation model.

Data and Resources

Cite this as

Omri Avrahami, Ohad Fried, Dani Lischinski (2024). Dataset: Break-A-Scene: Extracting Multiple Concepts from a Single Image. https://doi.org/10.57702/pyd0pkxf

DOI retrieved: December 3, 2024

Additional Info

Field Value
Created December 3, 2024
Last update December 3, 2024
Defined In https://doi.org/10.1145/3610548.3618154
Author Omri Avrahami
More Authors
Ohad Fried
Dani Lischinski
Homepage https://api.semanticscholar.org/CorpusID:256416326