Locate, Assign, Refine: Taming Customized Promptable Image Inpainting
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_ | 1866909463501340672 |
|---|---|
| author | Pan, Yulin Mao, Chaojie Jiang, Zeyinzi Han, Zhen Zhang, Jingfeng He, Xiangteng |
| author_facet | Pan, Yulin Mao, Chaojie Jiang, Zeyinzi Han, Zhen Zhang, Jingfeng He, Xiangteng |
| contents | Prior studies have made significant progress in image inpainting guided by either text description or subject image. However, the research on inpainting with flexible guidance or control, i.e., text-only, image-only, and their combination, is still in the early stage. Therefore, in this paper, we introduce the multimodal promptable image inpainting project: a new task model, and data for taming customized image inpainting. We propose LAR-Gen, a novel approach for image inpainting that enables seamless inpainting of specific region in images corresponding to the mask prompt, incorporating both the text prompt and image prompt. Our LAR-Gen adopts a coarse-to-fine manner to ensure the context consistency of source image, subject identity consistency, local semantic consistency to the text description, and smoothness consistency. It consists of three mechanisms: (i) Locate mechanism: concatenating the noise with masked scene image to achieve precise regional editing, (ii) Assign mechanism: employing decoupled cross-attention mechanism to accommodate multi-modal guidance, and (iii) Refine mechanism: using a novel RefineNet to supplement subject details. Additionally, to address the issue of scarce training data, we introduce a novel data engine to automatically extract substantial pairs of data consisting of local text prompts and corresponding visual instances from a vast image data, leveraging publicly available pre-trained large models. Extensive experiments and various application scenarios demonstrate the superiority of LAR-Gen in terms of both identity preservation and text semantic consistency. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_19534 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Locate, Assign, Refine: Taming Customized Promptable Image Inpainting Pan, Yulin Mao, Chaojie Jiang, Zeyinzi Han, Zhen Zhang, Jingfeng He, Xiangteng Computer Vision and Pattern Recognition Prior studies have made significant progress in image inpainting guided by either text description or subject image. However, the research on inpainting with flexible guidance or control, i.e., text-only, image-only, and their combination, is still in the early stage. Therefore, in this paper, we introduce the multimodal promptable image inpainting project: a new task model, and data for taming customized image inpainting. We propose LAR-Gen, a novel approach for image inpainting that enables seamless inpainting of specific region in images corresponding to the mask prompt, incorporating both the text prompt and image prompt. Our LAR-Gen adopts a coarse-to-fine manner to ensure the context consistency of source image, subject identity consistency, local semantic consistency to the text description, and smoothness consistency. It consists of three mechanisms: (i) Locate mechanism: concatenating the noise with masked scene image to achieve precise regional editing, (ii) Assign mechanism: employing decoupled cross-attention mechanism to accommodate multi-modal guidance, and (iii) Refine mechanism: using a novel RefineNet to supplement subject details. Additionally, to address the issue of scarce training data, we introduce a novel data engine to automatically extract substantial pairs of data consisting of local text prompts and corresponding visual instances from a vast image data, leveraging publicly available pre-trained large models. Extensive experiments and various application scenarios demonstrate the superiority of LAR-Gen in terms of both identity preservation and text semantic consistency. |
| title | Locate, Assign, Refine: Taming Customized Promptable Image Inpainting |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2403.19534 |