Guardado en:
Detalles Bibliográficos
Autores principales: Li, Fan, Zhang, Zixiao, Huang, Yi, Liu, Jianzhuang, Pei, Renjing, Shao, Bin, Xu, Songcen
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:https://arxiv.org/abs/2410.10207
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866929540942528512
author Li, Fan
Zhang, Zixiao
Huang, Yi
Liu, Jianzhuang
Pei, Renjing
Shao, Bin
Xu, Songcen
author_facet Li, Fan
Zhang, Zixiao
Huang, Yi
Liu, Jianzhuang
Pei, Renjing
Shao, Bin
Xu, Songcen
contents The traditional image inpainting task aims to restore corrupted regions by referencing surrounding background and foreground. However, the object erasure task, which is in increasing demand, aims to erase objects and generate harmonious background. Previous GAN-based inpainting methods struggle with intricate texture generation. Emerging diffusion model-based algorithms, such as Stable Diffusion Inpainting, exhibit the capability to generate novel content, but they often produce incongruent results at the locations of the erased objects and require high-quality text prompt inputs. To address these challenges, we introduce MagicEraser, a diffusion model-based framework tailored for the object erasure task. It consists of two phases: content initialization and controllable generation. In the latter phase, we develop two plug-and-play modules called prompt tuning and semantics-aware attention refocus. Additionally, we propose a data construction strategy that generates training data specially suitable for this task. MagicEraser achieves fine and effective control of content generation while mitigating undesired artifacts. Experimental results highlight a valuable advancement of our approach in the object erasure task.
format Preprint
id arxiv_https___arxiv_org_abs_2410_10207
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle MagicEraser: Erasing Any Objects via Semantics-Aware Control
Li, Fan
Zhang, Zixiao
Huang, Yi
Liu, Jianzhuang
Pei, Renjing
Shao, Bin
Xu, Songcen
Computer Vision and Pattern Recognition
The traditional image inpainting task aims to restore corrupted regions by referencing surrounding background and foreground. However, the object erasure task, which is in increasing demand, aims to erase objects and generate harmonious background. Previous GAN-based inpainting methods struggle with intricate texture generation. Emerging diffusion model-based algorithms, such as Stable Diffusion Inpainting, exhibit the capability to generate novel content, but they often produce incongruent results at the locations of the erased objects and require high-quality text prompt inputs. To address these challenges, we introduce MagicEraser, a diffusion model-based framework tailored for the object erasure task. It consists of two phases: content initialization and controllable generation. In the latter phase, we develop two plug-and-play modules called prompt tuning and semantics-aware attention refocus. Additionally, we propose a data construction strategy that generates training data specially suitable for this task. MagicEraser achieves fine and effective control of content generation while mitigating undesired artifacts. Experimental results highlight a valuable advancement of our approach in the object erasure task.
title MagicEraser: Erasing Any Objects via Semantics-Aware Control
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2410.10207