作者位次 #5/12ACL 2026Poster· Natural Language Processing
I 2 E : From Image Pixels to Actionable Interactive Environments for Text-Guided Image Editing
Jinghan Yu · Junhao Xiao · Chenyu Zhu · Jiaming Li · Jia Li · HanMing Deng · Xirui Wang · Guoli Jia · Jianjun Li · Xiang Bai · Bowen Zhou · Zhiyuan Ma
摘要
Existing text-guided image editing methods primarily rely on end-to-end pixel-level inpainting paradigm. Despite its success in simple scenarios, this paradigm still significantly struggles with compositional editing tasks that require precise local control and complex multi-object spatial reason...