Edicho: Consistent Image Editing in the Wild
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916565669117952 |
|---|---|
| author | Bai, Qingyan Ouyang, Hao Xu, Yinghao Wang, Qiuyu Yang, Ceyuan Cheng, Ka Leong Shen, Yujun Chen, Qifeng |
| author_facet | Bai, Qingyan Ouyang, Hao Xu, Yinghao Wang, Qiuyu Yang, Ceyuan Cheng, Ka Leong Shen, Yujun Chen, Qifeng |
| contents | As a verified need, consistent editing across in-the-wild images remains a technical challenge arising from various unmanageable factors, like object poses, lighting conditions, and photography environments. Edicho steps in with a training-free solution based on diffusion models, featuring a fundamental design principle of using explicit image correspondence to direct editing. Specifically, the key components include an attention manipulation module and a carefully refined classifier-free guidance (CFG) denoising strategy, both of which take into account the pre-estimated correspondence. Such an inference-time algorithm enjoys a plug-and-play nature and is compatible to most diffusion-based editing methods, such as ControlNet and BrushNet. Extensive results demonstrate the efficacy of Edicho in consistent cross-image editing under diverse settings. We will release the code to facilitate future studies. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_21079 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Edicho: Consistent Image Editing in the Wild Bai, Qingyan Ouyang, Hao Xu, Yinghao Wang, Qiuyu Yang, Ceyuan Cheng, Ka Leong Shen, Yujun Chen, Qifeng Computer Vision and Pattern Recognition As a verified need, consistent editing across in-the-wild images remains a technical challenge arising from various unmanageable factors, like object poses, lighting conditions, and photography environments. Edicho steps in with a training-free solution based on diffusion models, featuring a fundamental design principle of using explicit image correspondence to direct editing. Specifically, the key components include an attention manipulation module and a carefully refined classifier-free guidance (CFG) denoising strategy, both of which take into account the pre-estimated correspondence. Such an inference-time algorithm enjoys a plug-and-play nature and is compatible to most diffusion-based editing methods, such as ControlNet and BrushNet. Extensive results demonstrate the efficacy of Edicho in consistent cross-image editing under diverse settings. We will release the code to facilitate future studies. |
| title | Edicho: Consistent Image Editing in the Wild |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2412.21079 |