FlexiEdit: Frequency-Aware Latent Refinement for Enhanced Non-Rigid Editing

TL;DR

FlexiEdit improves non-rigid image editing by refining DDIM latent representations, especially reducing high-frequency components, to better preserve original image features and accurately reflect input prompts.

Contribution

The paper introduces FlexiEdit, a novel method that enhances non-rigid image editing by refining DDIM latent space to improve fidelity and layout adjustments.

Findings

Enhanced editing fidelity demonstrated in experiments

Better preservation of original image features

Improved handling of complex non-rigid edits

Abstract

Current image editing methods primarily utilize DDIM Inversion, employing a two-branch diffusion approach to preserve the attributes and layout of the original image. However, these methods encounter challenges with non-rigid edits, which involve altering the image's layout or structure. Our comprehensive analysis reveals that the high-frequency components of DDIM latent, crucial for retaining the original image's key features and layout, significantly contribute to these limitations. Addressing this, we introduce FlexiEdit, which enhances fidelity to input text prompts by refining DDIM latent, by reducing high-frequency components in targeted editing areas. FlexiEdit comprises two key components: (1) Latent Refinement, which modifies DDIM latent to better accommodate layout adjustments, and (2) Edit Fidelity Enhancement via Re-inversion, aimed at ensuring the edits more accurately reflect the input text prompts. Our approach represents notable progress in image editing, particularly in performing complex non-rigid edits, showcasing its enhanced capability through comparative experiments.