Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2506.07992 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915333931008000 |
|---|---|
| author | Lu, Haoguang Chen, Jiacheng Yang, Zhenguo Gnanha, Aurele Tohokantche Wang, Fu Lee Qing, Li Mao, Xudong |
| author_facet | Lu, Haoguang Chen, Jiacheng Yang, Zhenguo Gnanha, Aurele Tohokantche Wang, Fu Lee Qing, Li Mao, Xudong |
| contents | Recent advancements in text-guided image editing have achieved notable success by leveraging natural language prompts for fine-grained semantic control. However, certain editing semantics are challenging to specify precisely using textual descriptions alone. A practical alternative involves learning editing semantics from paired source-target examples. Existing exemplar-based editing methods still rely on text prompts describing the change within paired examples or learning implicit text-based editing instructions. In this paper, we introduce PairEdit, a novel visual editing method designed to effectively learn complex editing semantics from a limited number of image pairs or even a single image pair, without using any textual guidance. We propose a target noise prediction that explicitly models semantic variations within paired images through a guidance direction term. Moreover, we introduce a content-preserving noise schedule to facilitate more effective semantic learning. We also propose optimizing distinct LoRAs to disentangle the learning of semantic variations from content. Extensive qualitative and quantitative evaluations demonstrate that PairEdit successfully learns intricate semantics while significantly improving content consistency compared to baseline methods. Code will be available at https://github.com/xudonmao/PairEdit. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_07992 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | PairEdit: Learning Semantic Variations for Exemplar-based Image Editing Lu, Haoguang Chen, Jiacheng Yang, Zhenguo Gnanha, Aurele Tohokantche Wang, Fu Lee Qing, Li Mao, Xudong Computer Vision and Pattern Recognition Recent advancements in text-guided image editing have achieved notable success by leveraging natural language prompts for fine-grained semantic control. However, certain editing semantics are challenging to specify precisely using textual descriptions alone. A practical alternative involves learning editing semantics from paired source-target examples. Existing exemplar-based editing methods still rely on text prompts describing the change within paired examples or learning implicit text-based editing instructions. In this paper, we introduce PairEdit, a novel visual editing method designed to effectively learn complex editing semantics from a limited number of image pairs or even a single image pair, without using any textual guidance. We propose a target noise prediction that explicitly models semantic variations within paired images through a guidance direction term. Moreover, we introduce a content-preserving noise schedule to facilitate more effective semantic learning. We also propose optimizing distinct LoRAs to disentangle the learning of semantic variations from content. Extensive qualitative and quantitative evaluations demonstrate that PairEdit successfully learns intricate semantics while significantly improving content consistency compared to baseline methods. Code will be available at https://github.com/xudonmao/PairEdit. |
| title | PairEdit: Learning Semantic Variations for Exemplar-based Image Editing |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2506.07992 |