RefEdit-Bench measures referring-expression image editing; the RefEdit model, trained on 20K synthetic triplets, reports state-of-the-art results over million-scale baselines.
In- structpix2pix: Learning to follow image editing instructions
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
RefEdit: A Benchmark and Method for Improving Instruction-based Image Editing Model on Referring Expressions
RefEdit-Bench measures referring-expression image editing; the RefEdit model, trained on 20K synthetic triplets, reports state-of-the-art results over million-scale baselines.