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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Hou, Xingzhong, Wu, Jie, Liu, Boxiao, Zhang, Yi, Song, Guanglu, Liu, Yunpeng, Liu, Yu, You, Haihang
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918059168497664
author Hou, Xingzhong
Wu, Jie
Liu, Boxiao
Zhang, Yi
Song, Guanglu
Liu, Yunpeng
Liu, Yu
You, Haihang
author_facet Hou, Xingzhong
Wu, Jie
Liu, Boxiao
Zhang, Yi
Song, Guanglu
Liu, Yunpeng
Liu, Yu
You, Haihang
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2506_12530
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Towards Seamless Borders: A Method for Mitigating Inconsistencies in Image Inpainting and Outpainting
Hou, Xingzhong
Wu, Jie
Liu, Boxiao
Zhang, Yi
Song, Guanglu
Liu, Yunpeng
Liu, Yu
You, Haihang
Computer Vision and Pattern Recognition
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.
title Towards Seamless Borders: A Method for Mitigating Inconsistencies in Image Inpainting and Outpainting
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2506.12530