摘要
近年来,图像生成领域的技术取得了显著进展,但图像修复任务中修复区域与未修改区域之间的一致性仍是一个普遍存在的挑战。本文旨在提出一种基于扩散模型的两阶段图像修复模型(Diff-2sIR),以提升修复区域与未修复区域的一致性,进一步提高图像修复质量。本文以扩散模型理论为基础,设计了一种两阶段修复框架。通过改进U-Net架构和扩散模型采样算法,对初步修复结果进行二次细化修复,缓解了修复区域与未修复区域之间的不一致性问题。在CelebA-HQ数据集的人脸修复任务中,Diff-2sIR模型取得了最优FID分数(2.92),显著提升了修复质量。实验结果表明,该模型在指导模块修复结果的基础上进一步细化修复效果,展现了卓越的性能。本文提出的Diff-2sIR模型有效解决了修复区域与未修复区域之间的不一致性问题,为图像修复任务提供了一种新的解决方案,具有重要的理论意义和应用价值。
In recent years,significant progress has been made in the field of image generation,but the consistency between the repaired and unmodified regions remains a common challenge in image inpainting tasks.This paper proposes a two-stage image inpainting model based on diffusion models(Diff-2sIR)to enhance the consistency between the repaired and unmodified regions,thereby improving the overall quality of image inpainting.Based on the theory of diffusion models,a two-stage inpainting framework is designed.By improving the U-Net architecture and the diffusion model sampling algorithm,the initial inpainting results are further refined in a second stage,alleviating the inconsistency between the repaired and unmodified regions.In the face inpainting task on the CelebA-HQ dataset,the Diff-2sIR model achieves the best FID score(2.92),significantly improving the inpainting quality.Experimental results show that the model further refines the inpainting results based on the guidance module,demonstrating exceptional performance.The Diff-2sIR model effectively addresses the inconsistency between the repaired and unmodified regions,providing a new solution for image inpainting tasks,with significant theoretical and practical implications.
作者
张绪
胡峻峰
Zhang Xu;Hu Junfeng(College of Computer Science and Control Engineering,Northeast Forestry University,Harbin 150040,China)
出处
《电子测量技术》
北大核心
2025年第17期142-150,共9页
Electronic Measurement Technology
基金
国家自然科学基金(32202147)
中央高校基本科研专项资金项目(2572019BF09)资助。
关键词
图像修复
图像生成
扩散模型
二阶段模型
image inpainting
image generation
diffusion model
two-stage model
