Saved in:
Bibliographic Details
Main Authors: Yang, Kaixiang, Shen, Boyang, Li, Xin, Dai, Yuchen, Luo, Yuxuan, Ma, Yueran, Fang, Wei, Li, Qiang, Wang, Zhiwei
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2511.12151
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911267799695360
author Yang, Kaixiang
Shen, Boyang
Li, Xin
Dai, Yuchen
Luo, Yuxuan
Ma, Yueran
Fang, Wei
Li, Qiang
Wang, Zhiwei
author_facet Yang, Kaixiang
Shen, Boyang
Li, Xin
Dai, Yuchen
Luo, Yuxuan
Ma, Yueran
Fang, Wei
Li, Qiang
Wang, Zhiwei
contents Text-guided image editing has advanced rapidly with the rise of diffusion models. While flow-based inversion-free methods offer high efficiency by avoiding latent inversion, they often fail to effectively integrate source information, leading to poor background preservation, spatial inconsistencies, and over-editing due to the lack of effective integration of source information. In this paper, we present FIA-Edit, a novel inversion-free framework that achieves high-fidelity and semantically precise edits through a Frequency-Interactive Attention. Specifically, we design two key components: (1) a Frequency Representation Interaction (FRI) module that enhances cross-domain alignment by exchanging frequency components between source and target features within self-attention, and (2) a Feature Injection (FIJ) module that explicitly incorporates source-side queries, keys, values, and text embeddings into the target branch's cross-attention to preserve structure and semantics. Comprehensive and extensive experiments demonstrate that FIA-Edit supports high-fidelity editing at low computational cost (~6s per 512 * 512 image on an RTX 4090) and consistently outperforms existing methods across diverse tasks in visual quality, background fidelity, and controllability. Furthermore, we are the first to extend text-guided image editing to clinical applications. By synthesizing anatomically coherent hemorrhage variations in surgical images, FIA-Edit opens new opportunities for medical data augmentation and delivers significant gains in downstream bleeding classification. Our project is available at: https://github.com/kk42yy/FIA-Edit.
format Preprint
id arxiv_https___arxiv_org_abs_2511_12151
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle FIA-Edit: Frequency-Interactive Attention for Efficient and High-Fidelity Inversion-Free Text-Guided Image Editing
Yang, Kaixiang
Shen, Boyang
Li, Xin
Dai, Yuchen
Luo, Yuxuan
Ma, Yueran
Fang, Wei
Li, Qiang
Wang, Zhiwei
Computer Vision and Pattern Recognition
Text-guided image editing has advanced rapidly with the rise of diffusion models. While flow-based inversion-free methods offer high efficiency by avoiding latent inversion, they often fail to effectively integrate source information, leading to poor background preservation, spatial inconsistencies, and over-editing due to the lack of effective integration of source information. In this paper, we present FIA-Edit, a novel inversion-free framework that achieves high-fidelity and semantically precise edits through a Frequency-Interactive Attention. Specifically, we design two key components: (1) a Frequency Representation Interaction (FRI) module that enhances cross-domain alignment by exchanging frequency components between source and target features within self-attention, and (2) a Feature Injection (FIJ) module that explicitly incorporates source-side queries, keys, values, and text embeddings into the target branch's cross-attention to preserve structure and semantics. Comprehensive and extensive experiments demonstrate that FIA-Edit supports high-fidelity editing at low computational cost (~6s per 512 * 512 image on an RTX 4090) and consistently outperforms existing methods across diverse tasks in visual quality, background fidelity, and controllability. Furthermore, we are the first to extend text-guided image editing to clinical applications. By synthesizing anatomically coherent hemorrhage variations in surgical images, FIA-Edit opens new opportunities for medical data augmentation and delivers significant gains in downstream bleeding classification. Our project is available at: https://github.com/kk42yy/FIA-Edit.
title FIA-Edit: Frequency-Interactive Attention for Efficient and High-Fidelity Inversion-Free Text-Guided Image Editing
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2511.12151