Towards Seamless Borders: A Method for Mitigating Inconsistencies in Image Inpainting and Outpainting

TL;DR

This paper introduces two novel techniques to improve the seamlessness and visual coherence of diffusion-based image inpainting, addressing color mismatches and blending issues.

Contribution

It presents a modified Variational Autoencoder and a two-step training strategy to enhance continuity and reduce discrepancies in image inpainting.

Findings

Reduced color mismatches in inpainted images

Improved blending of generated and original content

High-quality, coherent inpainting results

Abstract

Image inpainting is the task of reconstructing missing or damaged parts of an image in a way that seamlessly blends with the surrounding content. With the advent of advanced generative models, especially diffusion models and generative adversarial networks, inpainting has achieved remarkable improvements in visual quality and coherence. However, achieving seamless continuity remains a significant challenge. In this work, we propose two novel methods to address discrepancy issues in diffusion-based inpainting models. First, we introduce a modified Variational Autoencoder that corrects color imbalances, ensuring that the final inpainted results are free of color mismatches. Second, we propose a two-step training strategy that improves the blending of generated and existing image content during the diffusion process. Through extensive experiments, we demonstrate that our methods effectively reduce discontinuity and produce high-quality inpainting results that are coherent and visually appealing.