Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2407.17847 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917866696081408 |
|---|---|
| author | Jiang, Pengfei Lin, Mingbao Chao, Fei |
| author_facet | Jiang, Pengfei Lin, Mingbao Chao, Fei |
| contents | Current methods commonly utilize three-branch structures of inversion, reconstruction, and editing, to tackle consistent image editing task. However, these methods lack control over the generation position of the edited object and have issues with background preservation. To overcome these limitations, we propose a tuning-free method with only two branches: inversion and editing. This approach allows users to simultaneously edit the object's action and control the generation position of the edited object. Additionally, it achieves improved background preservation. Specifically, we transfer the edited object information to the target area and repair or preserve the background of other areas during the inversion process at a specific time step. In the editing stage, we use the image features in self-attention to query the key and value of the corresponding time step in the inversion to achieve consistent image editing. Impressive image editing results and quantitative evaluation demonstrate the effectiveness of our method. The code is available at https://github.com/mobiushy/move-act. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_17847 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Move and Act: Enhanced Object Manipulation and Background Integrity for Image Editing Jiang, Pengfei Lin, Mingbao Chao, Fei Computer Vision and Pattern Recognition Current methods commonly utilize three-branch structures of inversion, reconstruction, and editing, to tackle consistent image editing task. However, these methods lack control over the generation position of the edited object and have issues with background preservation. To overcome these limitations, we propose a tuning-free method with only two branches: inversion and editing. This approach allows users to simultaneously edit the object's action and control the generation position of the edited object. Additionally, it achieves improved background preservation. Specifically, we transfer the edited object information to the target area and repair or preserve the background of other areas during the inversion process at a specific time step. In the editing stage, we use the image features in self-attention to query the key and value of the corresponding time step in the inversion to achieve consistent image editing. Impressive image editing results and quantitative evaluation demonstrate the effectiveness of our method. The code is available at https://github.com/mobiushy/move-act. |
| title | Move and Act: Enhanced Object Manipulation and Background Integrity for Image Editing |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2407.17847 |