Rethinking Where to Edit: Task-Aware Localization for Instruction-Based Image Editing

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	He, Jingxuan, Wang, Xiyu, Zheng, Mengyu, Zeng, Xiangyu, Wang, Yunke, Xu, Chang
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2604.20258