DragText: Rethinking Text Embedding in Point-based Image Editing
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866910726070730752 |
|---|---|
| author | Choi, Gayoon Jeong, Taejin Hong, Sujung Hwang, Seong Jae |
| author_facet | Choi, Gayoon Jeong, Taejin Hong, Sujung Hwang, Seong Jae |
| contents | Point-based image editing enables accurate and flexible control through content dragging. However, the role of text embedding during the editing process has not been thoroughly investigated. A significant aspect that remains unexplored is the interaction between text and image embeddings. During the progressive editing in a diffusion model, the text embedding remains constant. As the image embedding increasingly diverges from its initial state, the discrepancy between the image and text embeddings presents a significant challenge. In this study, we found that the text prompt significantly influences the dragging process, particularly in maintaining content integrity and achieving the desired manipulation. Upon these insights, we propose DragText, which optimizes text embedding in conjunction with the dragging process to pair with the modified image embedding. Simultaneously, we regularize the text optimization process to preserve the integrity of the original text prompt. Our approach can be seamlessly integrated with existing diffusion-based drag methods, enhancing performance with only a few lines of code. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_17843 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | DragText: Rethinking Text Embedding in Point-based Image Editing Choi, Gayoon Jeong, Taejin Hong, Sujung Hwang, Seong Jae Computer Vision and Pattern Recognition Artificial Intelligence Point-based image editing enables accurate and flexible control through content dragging. However, the role of text embedding during the editing process has not been thoroughly investigated. A significant aspect that remains unexplored is the interaction between text and image embeddings. During the progressive editing in a diffusion model, the text embedding remains constant. As the image embedding increasingly diverges from its initial state, the discrepancy between the image and text embeddings presents a significant challenge. In this study, we found that the text prompt significantly influences the dragging process, particularly in maintaining content integrity and achieving the desired manipulation. Upon these insights, we propose DragText, which optimizes text embedding in conjunction with the dragging process to pair with the modified image embedding. Simultaneously, we regularize the text optimization process to preserve the integrity of the original text prompt. Our approach can be seamlessly integrated with existing diffusion-based drag methods, enhancing performance with only a few lines of code. |
| title | DragText: Rethinking Text Embedding in Point-based Image Editing |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2407.17843 |