Guardado en:
Detalles Bibliográficos
Autores principales: Chen, Songyan, Huang, Jiancheng
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:https://arxiv.org/abs/2401.03433
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866909064309506048
author Chen, Songyan
Huang, Jiancheng
author_facet Chen, Songyan
Huang, Jiancheng
contents Text-conditional image editing based on large diffusion generative model has attracted the attention of both the industry and the research community. Most existing methods are non-reference editing, with the user only able to provide a source image and text prompt. However, it restricts user's control over the characteristics of editing outcome. To increase user freedom, we propose a new task called Specific Reference Condition Real Image Editing, which allows user to provide a reference image to further control the outcome, such as replacing an object with a particular one. To accomplish this, we propose a fast baseline method named SpecRef. Specifically, we design a Specific Reference Attention Controller to incorporate features from the reference image, and adopt a mask mechanism to prevent interference between editing and non-editing regions. We evaluate SpecRef on typical editing tasks and show that it can achieve satisfactory performance. The source code is available on https://github.com/jingjiqinggong/specp2p.
format Preprint
id arxiv_https___arxiv_org_abs_2401_03433
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle SpecRef: A Fast Training-free Baseline of Specific Reference-Condition Real Image Editing
Chen, Songyan
Huang, Jiancheng
Computer Vision and Pattern Recognition
Text-conditional image editing based on large diffusion generative model has attracted the attention of both the industry and the research community. Most existing methods are non-reference editing, with the user only able to provide a source image and text prompt. However, it restricts user's control over the characteristics of editing outcome. To increase user freedom, we propose a new task called Specific Reference Condition Real Image Editing, which allows user to provide a reference image to further control the outcome, such as replacing an object with a particular one. To accomplish this, we propose a fast baseline method named SpecRef. Specifically, we design a Specific Reference Attention Controller to incorporate features from the reference image, and adopt a mask mechanism to prevent interference between editing and non-editing regions. We evaluate SpecRef on typical editing tasks and show that it can achieve satisfactory performance. The source code is available on https://github.com/jingjiqinggong/specp2p.
title SpecRef: A Fast Training-free Baseline of Specific Reference-Condition Real Image Editing
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2401.03433