Realistic Noise Synthesis with Diffusion Models

Bibliographic Details
Title:	Realistic Noise Synthesis with Diffusion Models
Authors:	Wu, Qi, Han, Mingyan, Jiang, Ting, Jiang, Chengzhi, Luo, Jinting, Jiang, Man, Fan, Haoqiang, Liu, Shuaicheng
Publication Year:	2023
Collection:	Computer Science
Subject Terms:	Computer Science - Computer Vision and Pattern Recognition, Electrical Engineering and Systems Science - Image and Video Processing
More Details:	Deep denoising models require extensive real-world training data, which is challenging to acquire. Current noise synthesis techniques struggle to accurately model complex noise distributions. We propose a novel Realistic Noise Synthesis Diffusor (RNSD) method using diffusion models to address these challenges. By encoding camera settings into a time-aware camera-conditioned affine modulation (TCCAM), RNSD generates more realistic noise distributions under various camera conditions. Additionally, RNSD integrates a multi-scale content-aware module (MCAM), enabling the generation of structured noise with spatial correlations across multiple frequencies. We also introduce Deep Image Prior Sampling (DIPS), a learnable sampling sequence based on depth image prior, which significantly accelerates the sampling process while maintaining the high quality of synthesized noise. Extensive experiments demonstrate that our RNSD method significantly outperforms existing techniques in synthesizing realistic noise under multiple metrics and improving image denoising performance. Comment: Accepted by AAAI25
Document Type:	Working Paper
Access URL:	http://arxiv.org/abs/2305.14022
Accession Number:	edsarx.2305.14022
Database:	arXiv

FullText	Text: Availability: 0 CustomLinks: – Url: http://arxiv.org/abs/2305.14022 Name: EDS - Arxiv Category: fullText Text: View this record from Arxiv MouseOverText: View this record from Arxiv – Url: https://resolver.ebsco.com/c/xy5jbn/result?sid=EBSCO:edsarx&genre=article&issn=&ISBN=&volume=&issue=&date=20230523&spage=&pages=&title=Realistic Noise Synthesis with Diffusion Models&atitle=Realistic%20Noise%20Synthesis%20with%20Diffusion%20Models&aulast=Wu%2C%20Qi&id=DOI: Name: Full Text Finder (for New FTF UI) (s8985755) Category: fullText Text: Find It @ SCU Libraries MouseOverText: Find It @ SCU Libraries
Header	DbId: edsarx DbLabel: arXiv An: edsarx.2305.14022 RelevancyScore: 1057 AccessLevel: 3 PubType: Report PubTypeId: report PreciseRelevancyScore: 1057.33178710938
IllustrationInfo
Items	– Name: Title Label: Title Group: Ti Data: Realistic Noise Synthesis with Diffusion Models – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Wu%2C+Qi%22">Wu, Qi</searchLink><br /><searchLink fieldCode="AR" term="%22Han%2C+Mingyan%22">Han, Mingyan</searchLink><br /><searchLink fieldCode="AR" term="%22Jiang%2C+Ting%22">Jiang, Ting</searchLink><br /><searchLink fieldCode="AR" term="%22Jiang%2C+Chengzhi%22">Jiang, Chengzhi</searchLink><br /><searchLink fieldCode="AR" term="%22Luo%2C+Jinting%22">Luo, Jinting</searchLink><br /><searchLink fieldCode="AR" term="%22Jiang%2C+Man%22">Jiang, Man</searchLink><br /><searchLink fieldCode="AR" term="%22Fan%2C+Haoqiang%22">Fan, Haoqiang</searchLink><br /><searchLink fieldCode="AR" term="%22Liu%2C+Shuaicheng%22">Liu, Shuaicheng</searchLink> – Name: DatePubCY Label: Publication Year Group: Date Data: 2023 – Name: Subset Label: Collection Group: HoldingsInfo Data: Computer Science – Name: Subject Label: Subject Terms Group: Su Data: <searchLink fieldCode="DE" term="%22Computer+Science+-+Computer+Vision+and+Pattern+Recognition%22">Computer Science - Computer Vision and Pattern Recognition</searchLink><br /><searchLink fieldCode="DE" term="%22Electrical+Engineering+and+Systems+Science+-+Image+and+Video+Processing%22">Electrical Engineering and Systems Science - Image and Video Processing</searchLink> – Name: Abstract Label: Description Group: Ab Data: Deep denoising models require extensive real-world training data, which is challenging to acquire. Current noise synthesis techniques struggle to accurately model complex noise distributions. We propose a novel Realistic Noise Synthesis Diffusor (RNSD) method using diffusion models to address these challenges. By encoding camera settings into a time-aware camera-conditioned affine modulation (TCCAM), RNSD generates more realistic noise distributions under various camera conditions. Additionally, RNSD integrates a multi-scale content-aware module (MCAM), enabling the generation of structured noise with spatial correlations across multiple frequencies. We also introduce Deep Image Prior Sampling (DIPS), a learnable sampling sequence based on depth image prior, which significantly accelerates the sampling process while maintaining the high quality of synthesized noise. Extensive experiments demonstrate that our RNSD method significantly outperforms existing techniques in synthesizing realistic noise under multiple metrics and improving image denoising performance.<br />Comment: Accepted by AAAI25 – Name: TypeDocument Label: Document Type Group: TypDoc Data: Working Paper – Name: URL Label: Access URL Group: URL Data: <link linkTarget="URL" linkTerm="http://arxiv.org/abs/2305.14022" linkWindow="_blank">http://arxiv.org/abs/2305.14022</link> – Name: AN Label: Accession Number Group: ID Data: edsarx.2305.14022
PLink	https://login.libproxy.scu.edu/login?url=https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&scope=site&db=edsarx&AN=edsarx.2305.14022
RecordInfo	BibRecord: BibEntity: Subjects: – SubjectFull: Computer Science - Computer Vision and Pattern Recognition Type: general – SubjectFull: Electrical Engineering and Systems Science - Image and Video Processing Type: general Titles: – TitleFull: Realistic Noise Synthesis with Diffusion Models Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Wu, Qi – PersonEntity: Name: NameFull: Han, Mingyan – PersonEntity: Name: NameFull: Jiang, Ting – PersonEntity: Name: NameFull: Jiang, Chengzhi – PersonEntity: Name: NameFull: Luo, Jinting – PersonEntity: Name: NameFull: Jiang, Man – PersonEntity: Name: NameFull: Fan, Haoqiang – PersonEntity: Name: NameFull: Liu, Shuaicheng IsPartOfRelationships: – BibEntity: Dates: – D: 23 M: 05 Type: published Y: 2023
ResultId	1