Edit Transfer: Learning Image Editing via Vision In-Context Relations
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912459136172032 |
|---|---|
| author | Chen, Lan Mao, Qi Gu, Yuchao Shou, Mike Zheng |
| author_facet | Chen, Lan Mao, Qi Gu, Yuchao Shou, Mike Zheng |
| contents | We introduce a new setting, Edit Transfer, where a model learns a transformation from just a single source-target example and applies it to a new query image. While text-based methods excel at semantic manipulations through textual prompts, they often struggle with precise geometric details (e.g., poses and viewpoint changes). Reference-based editing, on the other hand, typically focuses on style or appearance and fails at non-rigid transformations. By explicitly learning the editing transformation from a source-target pair, Edit Transfer mitigates the limitations of both text-only and appearance-centric references. Drawing inspiration from in-context learning in large language models, we propose a visual relation in-context learning paradigm, building upon a DiT-based text-to-image model. We arrange the edited example and the query image into a unified four-panel composite, then apply lightweight LoRA fine-tuning to capture complex spatial transformations from minimal examples. Despite using only 42 training samples, Edit Transfer substantially outperforms state-of-the-art TIE and RIE methods on diverse non-rigid scenarios, demonstrating the effectiveness of few-shot visual relation learning. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_13327 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Edit Transfer: Learning Image Editing via Vision In-Context Relations Chen, Lan Mao, Qi Gu, Yuchao Shou, Mike Zheng Computer Vision and Pattern Recognition We introduce a new setting, Edit Transfer, where a model learns a transformation from just a single source-target example and applies it to a new query image. While text-based methods excel at semantic manipulations through textual prompts, they often struggle with precise geometric details (e.g., poses and viewpoint changes). Reference-based editing, on the other hand, typically focuses on style or appearance and fails at non-rigid transformations. By explicitly learning the editing transformation from a source-target pair, Edit Transfer mitigates the limitations of both text-only and appearance-centric references. Drawing inspiration from in-context learning in large language models, we propose a visual relation in-context learning paradigm, building upon a DiT-based text-to-image model. We arrange the edited example and the query image into a unified four-panel composite, then apply lightweight LoRA fine-tuning to capture complex spatial transformations from minimal examples. Despite using only 42 training samples, Edit Transfer substantially outperforms state-of-the-art TIE and RIE methods on diverse non-rigid scenarios, demonstrating the effectiveness of few-shot visual relation learning. |
| title | Edit Transfer: Learning Image Editing via Vision In-Context Relations |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.13327 |