By learning edit regions from CLIP alignment on text-image pairs, the method performs instruction-driven editing without paired editing data, achieving competitive benchmark scores.
Introducing claude 3.5 sonnet
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
-
Beyond Editing Pairs: Fine-Grained Instructional Image Editing via Multi-Scale Learnable Regions
By learning edit regions from CLIP alignment on text-image pairs, the method performs instruction-driven editing without paired editing data, achieving competitive benchmark scores.