Complex Scene Breaking and Synthesis
1 papers with code • 0 benchmarks • 0 datasets
Given a single image with multiple concepts, annotated by loose segmentation masks, the method needs to learn a distinct token for each concept, and use natural language guidance to re-synthesize the individual concepts or combinations of them in various contexts.
These leaderboards are used to track progress in Complex Scene Breaking and Synthesis
Text-to-image model personalization aims to introduce a user-provided concept to the model, allowing its synthesis in diverse contexts.