Reversible Inversion for Training-Free Exemplar-guided Image Editing

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Yuke, Gao, Lianli, Zhang, Ji, Zeng, Pengpeng, Xiang, Lichuan, Wen, Hongkai, Shen, Heng Tao, Song, Jingkuan
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911712153698304
author Li, Yuke
Gao, Lianli
Zhang, Ji
Zeng, Pengpeng
Xiang, Lichuan
Wen, Hongkai
Shen, Heng Tao
Song, Jingkuan
author_facet Li, Yuke
Gao, Lianli
Zhang, Ji
Zeng, Pengpeng
Xiang, Lichuan
Wen, Hongkai
Shen, Heng Tao
Song, Jingkuan
contents Exemplar-guided Image Editing (EIE) aims to modify a source image according to a visual reference. Existing approaches often require large-scale pre-training to learn relationships between the source and reference images, incurring high computational costs. As a training-free alternative, inversion techniques can be used to map the source image into a latent space for manipulation. However, our empirical study reveals that standard inversion is sub-optimal for EIE, leading to poor quality and inefficiency. To tackle this challenge, we introduce \textbf{Reversible Inversion ({ReInversion})} for effective and efficient EIE. Specifically, ReInversion operates as a two-stage denoising process, which is first conditioned on the source image and subsequently on the reference. Besides, we introduce a Mask-Guided Selective Denoising (MSD) strategy to constrain edits to target regions, preserving the structural consistency of the background. Both qualitative and quantitative comparisons demonstrate that our ReInversion method achieves state-of-the-art EIE performance with the lowest computational overhead.
format Preprint
id arxiv_https___arxiv_org_abs_2512_01382
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Reversible Inversion for Training-Free Exemplar-guided Image Editing
Li, Yuke
Gao, Lianli
Zhang, Ji
Zeng, Pengpeng
Xiang, Lichuan
Wen, Hongkai
Shen, Heng Tao
Song, Jingkuan
Computer Vision and Pattern Recognition
Exemplar-guided Image Editing (EIE) aims to modify a source image according to a visual reference. Existing approaches often require large-scale pre-training to learn relationships between the source and reference images, incurring high computational costs. As a training-free alternative, inversion techniques can be used to map the source image into a latent space for manipulation. However, our empirical study reveals that standard inversion is sub-optimal for EIE, leading to poor quality and inefficiency. To tackle this challenge, we introduce \textbf{Reversible Inversion ({ReInversion})} for effective and efficient EIE. Specifically, ReInversion operates as a two-stage denoising process, which is first conditioned on the source image and subsequently on the reference. Besides, we introduce a Mask-Guided Selective Denoising (MSD) strategy to constrain edits to target regions, preserving the structural consistency of the background. Both qualitative and quantitative comparisons demonstrate that our ReInversion method achieves state-of-the-art EIE performance with the lowest computational overhead.
title Reversible Inversion for Training-Free Exemplar-guided Image Editing
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2512.01382