Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2406.17236 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910500253597696 |
|---|---|
| author | Liu, Aoyang Fan, Qingnan Qin, Shuai Gu, Hong Tang, Yansong |
| author_facet | Liu, Aoyang Fan, Qingnan Qin, Shuai Gu, Hong Tang, Yansong |
| contents | Although recent years have witnessed significant advancements in image editing thanks to the remarkable progress of text-to-image diffusion models, the problem of non-rigid image editing still presents its complexities and challenges. Existing methods often fail to achieve consistent results due to the absence of unique identity characteristics. Thus, learning a personalized identity prior might help with consistency in the edited results. In this paper, we explore a novel task: learning the personalized identity prior for text-based non-rigid image editing. To address the problems in jointly learning prior and editing the image, we present LIPE, a two-stage framework designed to customize the generative model utilizing a limited set of images of the same subject, and subsequently employ the model with learned prior for non-rigid image editing. Experimental results demonstrate the advantages of our approach in various editing scenarios over past related leading methods in qualitative and quantitative ways. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_17236 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | LIPE: Learning Personalized Identity Prior for Non-rigid Image Editing Liu, Aoyang Fan, Qingnan Qin, Shuai Gu, Hong Tang, Yansong Computer Vision and Pattern Recognition Although recent years have witnessed significant advancements in image editing thanks to the remarkable progress of text-to-image diffusion models, the problem of non-rigid image editing still presents its complexities and challenges. Existing methods often fail to achieve consistent results due to the absence of unique identity characteristics. Thus, learning a personalized identity prior might help with consistency in the edited results. In this paper, we explore a novel task: learning the personalized identity prior for text-based non-rigid image editing. To address the problems in jointly learning prior and editing the image, we present LIPE, a two-stage framework designed to customize the generative model utilizing a limited set of images of the same subject, and subsequently employ the model with learned prior for non-rigid image editing. Experimental results demonstrate the advantages of our approach in various editing scenarios over past related leading methods in qualitative and quantitative ways. |
| title | LIPE: Learning Personalized Identity Prior for Non-rigid Image Editing |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2406.17236 |