Reversible Inversion for Training-Free Exemplar-guided Image Editing

TL;DR

ReInversion is a training-free, two-stage denoising method for exemplar-guided image editing that improves quality, efficiency, and structural preservation over standard inversion techniques.

Contribution

The paper introduces ReInversion, a novel reversible inversion technique with a Mask-Guided Denoising strategy for superior, efficient exemplar-guided image editing without training.

Findings

Achieves state-of-the-art editing quality.

Reduces computational overhead significantly.

Effectively preserves background structure.

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.