ParallelEdits: Efficient Multi-object 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_ | 1866915271780859904 |
|---|---|
| author | Huang, Mingzhen Cai, Jialing Jia, Shan Lokhande, Vishnu Suresh Lyu, Siwei |
| author_facet | Huang, Mingzhen Cai, Jialing Jia, Shan Lokhande, Vishnu Suresh Lyu, Siwei |
| contents | Text-driven image synthesis has made significant advancements with the development of diffusion models, transforming how visual content is generated from text prompts. Despite these advances, text-driven image editing, a key area in computer graphics, faces unique challenges. A major challenge is making simultaneous edits across multiple objects or attributes. Applying these methods sequentially for multi-attribute edits increases computational demands and efficiency losses. In this paper, we address these challenges with significant contributions. Our main contribution is the development of ParallelEdits, a method that seamlessly manages simultaneous edits across multiple attributes. In contrast to previous approaches, ParallelEdits not only preserves the quality of single attribute edits but also significantly improves the performance of multitasking edits. This is achieved through innovative attention distribution mechanism and multi-branch design that operates across several processing heads. Additionally, we introduce the PIE-Bench++ dataset, an expansion of the original PIE-Bench dataset, to better support evaluating image-editing tasks involving multiple objects and attributes simultaneously. This dataset is a benchmark for evaluating text-driven image editing methods in multifaceted scenarios. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_00985 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | ParallelEdits: Efficient Multi-object Image Editing Huang, Mingzhen Cai, Jialing Jia, Shan Lokhande, Vishnu Suresh Lyu, Siwei Computer Vision and Pattern Recognition Text-driven image synthesis has made significant advancements with the development of diffusion models, transforming how visual content is generated from text prompts. Despite these advances, text-driven image editing, a key area in computer graphics, faces unique challenges. A major challenge is making simultaneous edits across multiple objects or attributes. Applying these methods sequentially for multi-attribute edits increases computational demands and efficiency losses. In this paper, we address these challenges with significant contributions. Our main contribution is the development of ParallelEdits, a method that seamlessly manages simultaneous edits across multiple attributes. In contrast to previous approaches, ParallelEdits not only preserves the quality of single attribute edits but also significantly improves the performance of multitasking edits. This is achieved through innovative attention distribution mechanism and multi-branch design that operates across several processing heads. Additionally, we introduce the PIE-Bench++ dataset, an expansion of the original PIE-Bench dataset, to better support evaluating image-editing tasks involving multiple objects and attributes simultaneously. This dataset is a benchmark for evaluating text-driven image editing methods in multifaceted scenarios. |
| title | ParallelEdits: Efficient Multi-object Image Editing |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2406.00985 |