collaborators

1 paper

cs.CV2026

SIGMA: Semantic-Difference Instruction-Grounding Mask Annotator for Text-Driven Image Manipulation Localization

Peiyu Zhuang, Jianquan Yang, Haodong Li +6

Text-driven image editing has advanced rapidly, but reliably localizing these manipulations requires image manipulation localization (IML) models trained on large pixel-annotated d…