Saved in:
| Main Author: | |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2503.04268 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929744714399744 |
|---|---|
| author | Jeon, Boseong |
| author_facet | Jeon, Boseong |
| contents | In this report, I present an inpainting framework named \textit{ControlFill}, which involves training two distinct prompts: one for generating plausible objects within a designated mask (\textit{creation}) and another for filling the region by extending the background (\textit{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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_04268 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | ControlFill: Spatially Adjustable Image Inpainting from Prompt Learning Jeon, Boseong Computer Vision and Pattern Recognition In this report, I present an inpainting framework named \textit{ControlFill}, which involves training two distinct prompts: one for generating plausible objects within a designated mask (\textit{creation}) and another for filling the region by extending the background (\textit{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. |
| title | ControlFill: Spatially Adjustable Image Inpainting from Prompt Learning |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.04268 |