Text-Driven Image Editing via Learnable Regions
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910396942647296 |
|---|---|
| author | Lin, Yuanze Chen, Yi-Wen Tsai, Yi-Hsuan Jiang, Lu Yang, Ming-Hsuan |
| author_facet | Lin, Yuanze Chen, Yi-Wen Tsai, Yi-Hsuan Jiang, Lu Yang, Ming-Hsuan |
| contents | Language has emerged as a natural interface for image editing. In this paper, we introduce a method for region-based image editing driven by textual prompts, without the need for user-provided masks or sketches. Specifically, our approach leverages an existing pre-trained text-to-image model and introduces a bounding box generator to identify the editing regions that are aligned with the textual prompts. We show that this simple approach enables flexible editing that is compatible with current image generation models, and is able to handle complex prompts featuring multiple objects, complex sentences, or lengthy paragraphs. We conduct an extensive user study to compare our method against state-of-the-art methods. The experiments demonstrate the competitive performance of our method in manipulating images with high fidelity and realism that correspond to the provided language descriptions. Our project webpage can be found at: https://yuanze-lin.me/LearnableRegions_page. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2311_16432 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Text-Driven Image Editing via Learnable Regions Lin, Yuanze Chen, Yi-Wen Tsai, Yi-Hsuan Jiang, Lu Yang, Ming-Hsuan Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning Language has emerged as a natural interface for image editing. In this paper, we introduce a method for region-based image editing driven by textual prompts, without the need for user-provided masks or sketches. Specifically, our approach leverages an existing pre-trained text-to-image model and introduces a bounding box generator to identify the editing regions that are aligned with the textual prompts. We show that this simple approach enables flexible editing that is compatible with current image generation models, and is able to handle complex prompts featuring multiple objects, complex sentences, or lengthy paragraphs. We conduct an extensive user study to compare our method against state-of-the-art methods. The experiments demonstrate the competitive performance of our method in manipulating images with high fidelity and realism that correspond to the provided language descriptions. Our project webpage can be found at: https://yuanze-lin.me/LearnableRegions_page. |
| title | Text-Driven Image Editing via Learnable Regions |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2311.16432 |