BrushEdit: All-In-One Image Inpainting and Editing

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Yaowei, Bian, Yuxuan, Ju, Xuan, Zhang, Zhaoyang, Zhuang, Junhao, Shan, Ying, Zou, Yuexian, Xu, Qiang
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916718947860480
author Li, Yaowei
Bian, Yuxuan
Ju, Xuan
Zhang, Zhaoyang
Zhuang, Junhao
Shan, Ying
Zou, Yuexian
Xu, Qiang
author_facet Li, Yaowei
Bian, Yuxuan
Ju, Xuan
Zhang, Zhaoyang
Zhuang, Junhao
Shan, Ying
Zou, Yuexian
Xu, Qiang
contents Image editing has advanced significantly with the development of diffusion models using both inversion-based and instruction-based methods. However, current inversion-based approaches struggle with big modifications (e.g., adding or removing objects) due to the structured nature of inversion noise, which hinders substantial changes. Meanwhile, instruction-based methods often constrain users to black-box operations, limiting direct interaction for specifying editing regions and intensity. To address these limitations, we propose BrushEdit, a novel inpainting-based instruction-guided image editing paradigm, which leverages multimodal large language models (MLLMs) and image inpainting models to enable autonomous, user-friendly, and interactive free-form instruction editing. Specifically, we devise a system enabling free-form instruction editing by integrating MLLMs and a dual-branch image inpainting model in an agent-cooperative framework to perform editing category classification, main object identification, mask acquisition, and editing area inpainting. Extensive experiments show that our framework effectively combines MLLMs and inpainting models, achieving superior performance across seven metrics including mask region preservation and editing effect coherence.
format Preprint
id arxiv_https___arxiv_org_abs_2412_10316
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle BrushEdit: All-In-One Image Inpainting and Editing
Li, Yaowei
Bian, Yuxuan
Ju, Xuan
Zhang, Zhaoyang
Zhuang, Junhao
Shan, Ying
Zou, Yuexian
Xu, Qiang
Computer Vision and Pattern Recognition
Artificial Intelligence
Image editing has advanced significantly with the development of diffusion models using both inversion-based and instruction-based methods. However, current inversion-based approaches struggle with big modifications (e.g., adding or removing objects) due to the structured nature of inversion noise, which hinders substantial changes. Meanwhile, instruction-based methods often constrain users to black-box operations, limiting direct interaction for specifying editing regions and intensity. To address these limitations, we propose BrushEdit, a novel inpainting-based instruction-guided image editing paradigm, which leverages multimodal large language models (MLLMs) and image inpainting models to enable autonomous, user-friendly, and interactive free-form instruction editing. Specifically, we devise a system enabling free-form instruction editing by integrating MLLMs and a dual-branch image inpainting model in an agent-cooperative framework to perform editing category classification, main object identification, mask acquisition, and editing area inpainting. Extensive experiments show that our framework effectively combines MLLMs and inpainting models, achieving superior performance across seven metrics including mask region preservation and editing effect coherence.
title BrushEdit: All-In-One Image Inpainting and Editing
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2412.10316