2 papers
cs.CV2024
ST-LDM: A Universal Framework for Text-Grounded Object Generation in Real Images
Xiangtian Xue, Jiasong Wu, Youyong Kong +2
We present a novel image editing scenario termed Text-grounded Object Generation (TOG), defined as generating a new object in the real image spatially conditioned by textual descri…
cs.CV2024
Rethinking Referring Object Removal
Xiangtian Xue, Jiasong Wu, Youyong Kong +2
Referring object removal refers to removing the specific object in an image referred by natural language expressions and filling the missing region with reasonable semantics. To ad…