

















Abstract: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.
| Subjects: | Computer Vision and Pattern Recognition (cs.CV) |
| Cite as: | arXiv:2512.01382 [cs.CV] |
| (or arXiv:2512.01382v4 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2512.01382 arXiv-issued DOI via DataCite |
From: Yuke Li [view email]
[v1]
Mon, 1 Dec 2025 07:56:06 UTC (8,224 KB)
[v2]
Fri, 6 Mar 2026 11:23:13 UTC (8,256 KB)
[v3]
Mon, 9 Mar 2026 06:06:22 UTC (8,230 KB)
[v4]
Sun, 24 May 2026 09:40:04 UTC (6,594 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理,仅供阅读参考。 原文来自 — 版权归原作者所有。