AI RESEARCH
Delta-Adapter: Scalable Exemplar-Based Image Editing with Single-Pair Supervision
arXiv CS.CV
•
ArXi:2605.07940v1 Announce Type: new Exemplar-based image editing applies a transformation defined by a source-target image pair to a new query image. Existing methods rely on a pair-of-pairs supervision paradigm, requiring two image pairs sharing the same edit semantics to data difficult to curate at scale and limits generalization across diverse edit types. We propose Delta-Adapter, a method that learns transferable editing semantics under single-pair supervision, requiring no textual guidance.