Exploiting Generative Diffusion Prior With Latent Low-Rank Regularization for Image Inpainting

IF 3.2 2区 工程技术 Q2 ENGINEERING, ELECTRICAL & ELECTRONIC
Zhentao Zou;Lin Chen;Xue Jiang;Abdelhak M. Zoubir
{"title":"Exploiting Generative Diffusion Prior With Latent Low-Rank Regularization for Image Inpainting","authors":"Zhentao Zou;Lin Chen;Xue Jiang;Abdelhak M. Zoubir","doi":"10.1109/LSP.2024.3453665","DOIUrl":null,"url":null,"abstract":"Generative diffusion models have recently shown impressive results in image restoration. However, the predicted noise from existing diffusion-based methods may be inaccurate, especially when the noise amplitude is small, thereby leading to sub-optimal results. In this letter, an unsupervised diffusion model with latent low-rank regularization is proposed to alleviate this challenge. In particular, we first create a latent low-rank space using self-supervised learning for each degraded images, from which we derive corresponding latent low-rank regularization. This regularization, combining with observed prior information and smoothness regularization, guides the reserve sampling process, resulting in the generation of high-quality images with fine-grained textures and fewer artifacts. In addition, by utilizing the pre-trained unconditional diffusion model, the proposed model reconstructs the missing pixels in a zero-shot manner, which does not need any reference images for additional training. Extensive experimental results demonstrate that our proposed method is superior to the self-supervised tensor completion methods and representative diffusion model-based image restoration methods.","PeriodicalId":13154,"journal":{"name":"IEEE Signal Processing Letters","volume":null,"pages":null},"PeriodicalIF":3.2000,"publicationDate":"2024-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE Signal Processing Letters","FirstCategoryId":"5","ListUrlMain":"https://ieeexplore.ieee.org/document/10663971/","RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ENGINEERING, ELECTRICAL & ELECTRONIC","Score":null,"Total":0}
引用次数: 0

Abstract

Generative diffusion models have recently shown impressive results in image restoration. However, the predicted noise from existing diffusion-based methods may be inaccurate, especially when the noise amplitude is small, thereby leading to sub-optimal results. In this letter, an unsupervised diffusion model with latent low-rank regularization is proposed to alleviate this challenge. In particular, we first create a latent low-rank space using self-supervised learning for each degraded images, from which we derive corresponding latent low-rank regularization. This regularization, combining with observed prior information and smoothness regularization, guides the reserve sampling process, resulting in the generation of high-quality images with fine-grained textures and fewer artifacts. In addition, by utilizing the pre-trained unconditional diffusion model, the proposed model reconstructs the missing pixels in a zero-shot manner, which does not need any reference images for additional training. Extensive experimental results demonstrate that our proposed method is superior to the self-supervised tensor completion methods and representative diffusion model-based image restoration methods.
利用潜在低秩正则化生成扩散先验进行图像绘制
生成扩散模型最近在图像修复方面取得了令人瞩目的成果。然而,现有的基于扩散的方法对噪声的预测可能并不准确,尤其是当噪声振幅较小时,从而导致效果不理想。在这封信中,我们提出了一种带有潜在低秩正则化的无监督扩散模型来缓解这一难题。具体来说,我们首先利用自监督学习为每幅降解图像创建一个潜在低阶空间,并从中推导出相应的潜在低阶正则化。这种正则化与观察到的先验信息和平滑度正则化相结合,指导后备采样过程,从而生成具有精细纹理和较少伪影的高质量图像。此外,通过利用预先训练好的无条件扩散模型,所提出的模型能以零镜头的方式重建缺失的像素,不需要任何参考图像来进行额外的训练。大量实验结果表明,我们提出的方法优于自监督张量补全方法和基于扩散模型的代表性图像修复方法。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
IEEE Signal Processing Letters
IEEE Signal Processing Letters 工程技术-工程:电子与电气
CiteScore
7.40
自引率
12.80%
发文量
339
审稿时长
2.8 months
期刊介绍: The IEEE Signal Processing Letters is a monthly, archival publication designed to provide rapid dissemination of original, cutting-edge ideas and timely, significant contributions in signal, image, speech, language and audio processing. Papers published in the Letters can be presented within one year of their appearance in signal processing conferences such as ICASSP, GlobalSIP and ICIP, and also in several workshop organized by the Signal Processing Society.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信