Meta-CoT: Enhancing Granularity and Generalization in Image Editing
Meta-CoT:提升图像编辑的粒度与泛化能力
机构 * Shenzhen International Graduate School, Tsinghua University(清华大学深圳国际研究生院) ; Hunyuan, Tencent(腾讯 Hunyuan)
AI总结 Meta-CoT通过双重分解提升图像编辑的粒度和泛化能力,通过任务-目标-理解能力三元组分解和五元基本元任务训练策略,显著提高编辑性能。
Comments Accepted by CVPR2026, Project Page: https://shiyi-zh0408.github.io/projectpages/Meta-CoT/