CorrFill: Enhancing Faithfulness in Reference-based Inpainting with Correspondence Guidance in Diffusion Models

TL;DR

CorrFill is a training-free module that improves the faithfulness of reference-based image inpainting by explicitly guiding the process with correspondence constraints, significantly enhancing existing diffusion model methods.

Contribution

Introduces CorrFill, a novel, training-free approach that incorporates correspondence guidance to improve geometric consistency in diffusion-based inpainting.

Findings

Significantly improves faithfulness to reference images

Enhances performance of multiple baseline diffusion methods

Effective in emphasizing geometric correlations

Abstract

In the task of reference-based image inpainting, an additional reference image is provided to restore a damaged target image to its original state. The advancement of diffusion models, particularly Stable Diffusion, allows for simple formulations in this task. However, existing diffusion-based methods often lack explicit constraints on the correlation between the reference and damaged images, resulting in lower faithfulness to the reference images in the inpainting results. In this work, we propose CorrFill, a training-free module designed to enhance the awareness of geometric correlations between the reference and target images. This enhancement is achieved by guiding the inpainting process with correspondence constraints estimated during inpainting, utilizing attention masking in self-attention layers and an objective function to update the input tensor according to the constraints. Experimental results demonstrate that CorrFill significantly enhances the performance of multiple baseline diffusion-based methods, including state-of-the-art approaches, by emphasizing faithfulness to the reference images.