ScribbleEdit is a synthetic dataset combining scribbles and text for training image editing models that produce spatially aligned and semantically consistent results.
UnSAMv2: Self-Supervised Learning Enables Segment Anything at Any Granularity
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
ScribbleEdit: Synthetic Data for Image Editing with Scribbles and Text
ScribbleEdit is a synthetic dataset combining scribbles and text for training image editing models that produce spatially aligned and semantically consistent results.