A$^\text{T}$A: Adaptive Transformation Agent for Text-Guided Subject-Position Variable Background Inpainting

• Main Authors: Tang, Yizhe, Sun, Zhimin, Du, Yuzhen, Yi, Ran, Lu, Guangben, Hu, Teng, Li, Luying, Ma, Lizhuang, Zou, Fangyuan
• Format: Journal Article
• Language: English
• Published: 02.04.2025
• Subjects: Computer Science - Computer Vision and Pattern Recognition
• DOI: 10.48550/arxiv.2504.01603

Image inpainting aims to fill the missing region of an image. Recently, there has been a surge of interest in foreground-conditioned background inpainting, a sub-task that fills the background of an image while the foreground subject and associated text prompt are provided. Existing background inpai...