2025/03/06 by Boseong Felipe Jeon, Jeon, Boseong
Computer Science · #Computer Vision and Pattern Recognition (cs.CV) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Face recognition and analysis #Generative Adversarial Networks and Image Synthesis
paper · pdf · doi:10.48550/arxiv.2503.04268
openalex publication_date 2025/03/06 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
In this report, I present an inpainting framework named ControlFill, which involves training two distinct prompts: one for generating plausible objects within a designated mask (creation) and another for filling the region by extending the background (removal). During the inference stage, these learned embeddings guide a diffusion network that operates without requiring heavy text encoders. By adjusting the relative significance of the two prompts and employing classifier-free guidance, users can control the intensity of removal or creation. Furthermore, I introduce a method to spatially vary the intensity of guidance by assigning different scales to individual pixels.