WIPUNet: A Physics-inspired Network with Weighted Inductive Biases for Image Denoising Article Swipe
In high-energy particle physics, collider measurements are contaminated by "pileup", overlapping soft interactions that obscure the hard-scatter signal of interest. Dedicated subtraction strategies exploit physical priors such as conservation, locality, and isolation. Inspired by this analogy, we investigate how such principles can inform image denoising by embedding physics-guided inductive biases into neural architectures. This paper is a proof of concept: rather than targeting state-of-the-art (SOTA) benchmarks, we ask whether physics-inspired priors improve robustness under strong corruption. We introduce a hierarchy of PU-inspired denoisers: a residual CNN with conservation constraints, its Gaussian-noise variants, and the Weighted Inductive Pileup-physics-inspired U-Network for Denoising (WIPUNet), which integrates these ideas into a UNet backbone. On CIFAR-10 with Gaussian noise at $σ\in\{15,25,50,75,100\}$, PU-inspired CNNs are competitive with standard baselines, while WIPUNet shows a \emph{widening margin} at higher noise. Complementary BSD500 experiments show the same trend, suggesting physics-inspired priors provide stability where purely data-driven models degrade. Our contributions are: (i) translating pileup-mitigation principles into modular inductive biases; (ii) integrating them into UNet; and (iii) demonstrating robustness gains at high noise without relying on heavy SOTA machinery.
Related Topics
Concepts
No concepts available.
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2509.05662
- https://arxiv.org/pdf/2509.05662
- OA Status
- green
- OpenAlex ID
- https://openalex.org/W4414763790
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4414763790Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2509.05662Digital Object Identifier
- Title
-
WIPUNet: A Physics-inspired Network with Weighted Inductive Biases for Image DenoisingWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2025Year of publication
- Publication date
-
2025-09-06Full publication date if available
- Authors
-
W. IslamList of authors in order
- Landing page
-
https://arxiv.org/abs/2509.05662Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2509.05662Direct link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
greenOpen access status per OpenAlex
- OA URL
-
https://arxiv.org/pdf/2509.05662Direct OA link when available
- Cited by
-
0Total citation count in OpenAlex
Full payload
| id | https://openalex.org/W4414763790 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2509.05662 |
| ids.doi | https://doi.org/10.48550/arxiv.2509.05662 |
| ids.openalex | https://openalex.org/W4414763790 |
| fwci | |
| type | preprint |
| title | WIPUNet: A Physics-inspired Network with Weighted Inductive Biases for Image Denoising |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T10320 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.9878000020980835 |
| topics[0].domain.id | https://openalex.org/domains/3 |
| topics[0].domain.display_name | Physical Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/1702 |
| topics[0].subfield.display_name | Artificial Intelligence |
| topics[0].display_name | Neural Networks and Applications |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2509.05662 |
| locations[0].is_oa | True |
| locations[0].source.id | https://openalex.org/S4306400194 |
| locations[0].source.issn | |
| locations[0].source.type | repository |
| locations[0].source.is_oa | True |
| locations[0].source.issn_l | |
| locations[0].source.is_core | False |
| locations[0].source.is_in_doaj | False |
| locations[0].source.display_name | arXiv (Cornell University) |
| locations[0].source.host_organization | https://openalex.org/I205783295 |
| locations[0].source.host_organization_name | Cornell University |
| locations[0].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[0].license | |
| locations[0].pdf_url | https://arxiv.org/pdf/2509.05662 |
| locations[0].version | submittedVersion |
| locations[0].raw_type | text |
| locations[0].license_id | |
| locations[0].is_accepted | False |
| locations[0].is_published | False |
| locations[0].raw_source_name | |
| locations[0].landing_page_url | http://arxiv.org/abs/2509.05662 |
| locations[1].id | doi:10.48550/arxiv.2509.05662 |
| locations[1].is_oa | True |
| locations[1].source.id | https://openalex.org/S4306400194 |
| locations[1].source.issn | |
| locations[1].source.type | repository |
| locations[1].source.is_oa | True |
| locations[1].source.issn_l | |
| locations[1].source.is_core | False |
| locations[1].source.is_in_doaj | False |
| locations[1].source.display_name | arXiv (Cornell University) |
| locations[1].source.host_organization | https://openalex.org/I205783295 |
| locations[1].source.host_organization_name | Cornell University |
| locations[1].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[1].license | |
| locations[1].pdf_url | |
| locations[1].version | |
| locations[1].raw_type | article |
| locations[1].license_id | |
| locations[1].is_accepted | False |
| locations[1].is_published | |
| locations[1].raw_source_name | |
| locations[1].landing_page_url | https://doi.org/10.48550/arxiv.2509.05662 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5080699493 |
| authorships[0].author.orcid | https://orcid.org/0000-0002-5624-5934 |
| authorships[0].author.display_name | W. Islam |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Islam, Wasikul |
| authorships[0].is_corresponding | True |
| has_content.pdf | False |
| has_content.grobid_xml | False |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://arxiv.org/pdf/2509.05662 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | WIPUNet: A Physics-inspired Network with Weighted Inductive Biases for Image Denoising |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T10320 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.9878000020980835 |
| primary_topic.domain.id | https://openalex.org/domains/3 |
| primary_topic.domain.display_name | Physical Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/1702 |
| primary_topic.subfield.display_name | Artificial Intelligence |
| primary_topic.display_name | Neural Networks and Applications |
| cited_by_count | 0 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2509.05662 |
| best_oa_location.is_oa | True |
| best_oa_location.source.id | https://openalex.org/S4306400194 |
| best_oa_location.source.issn | |
| best_oa_location.source.type | repository |
| best_oa_location.source.is_oa | True |
| best_oa_location.source.issn_l | |
| best_oa_location.source.is_core | False |
| best_oa_location.source.is_in_doaj | False |
| best_oa_location.source.display_name | arXiv (Cornell University) |
| best_oa_location.source.host_organization | https://openalex.org/I205783295 |
| best_oa_location.source.host_organization_name | Cornell University |
| best_oa_location.source.host_organization_lineage | https://openalex.org/I205783295 |
| best_oa_location.license | |
| best_oa_location.pdf_url | https://arxiv.org/pdf/2509.05662 |
| best_oa_location.version | submittedVersion |
| best_oa_location.raw_type | text |
| best_oa_location.license_id | |
| best_oa_location.is_accepted | False |
| best_oa_location.is_published | False |
| best_oa_location.raw_source_name | |
| best_oa_location.landing_page_url | http://arxiv.org/abs/2509.05662 |
| primary_location.id | pmh:oai:arXiv.org:2509.05662 |
| primary_location.is_oa | True |
| primary_location.source.id | https://openalex.org/S4306400194 |
| primary_location.source.issn | |
| primary_location.source.type | repository |
| primary_location.source.is_oa | True |
| primary_location.source.issn_l | |
| primary_location.source.is_core | False |
| primary_location.source.is_in_doaj | False |
| primary_location.source.display_name | arXiv (Cornell University) |
| primary_location.source.host_organization | https://openalex.org/I205783295 |
| primary_location.source.host_organization_name | Cornell University |
| primary_location.source.host_organization_lineage | https://openalex.org/I205783295 |
| primary_location.license | |
| primary_location.pdf_url | https://arxiv.org/pdf/2509.05662 |
| primary_location.version | submittedVersion |
| primary_location.raw_type | text |
| primary_location.license_id | |
| primary_location.is_accepted | False |
| primary_location.is_published | False |
| primary_location.raw_source_name | |
| primary_location.landing_page_url | http://arxiv.org/abs/2509.05662 |
| publication_date | 2025-09-06 |
| publication_year | 2025 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 56, 78, 83, 106, 126 |
| abstract_inverted_index.In | 0 |
| abstract_inverted_index.On | 109 |
| abstract_inverted_index.We | 76 |
| abstract_inverted_index.as | 27 |
| abstract_inverted_index.at | 114, 129, 170 |
| abstract_inverted_index.by | 8, 33, 45 |
| abstract_inverted_index.is | 55 |
| abstract_inverted_index.of | 18, 58, 80 |
| abstract_inverted_index.on | 175 |
| abstract_inverted_index.we | 36, 66 |
| abstract_inverted_index.(i) | 152 |
| abstract_inverted_index.CNN | 85 |
| abstract_inverted_index.Our | 149 |
| abstract_inverted_index.and | 30, 92, 165 |
| abstract_inverted_index.are | 6, 118 |
| abstract_inverted_index.ask | 67 |
| abstract_inverted_index.can | 41 |
| abstract_inverted_index.for | 98 |
| abstract_inverted_index.how | 38 |
| abstract_inverted_index.its | 89 |
| abstract_inverted_index.the | 15, 93, 136 |
| abstract_inverted_index.(ii) | 160 |
| abstract_inverted_index.CNNs | 117 |
| abstract_inverted_index.SOTA | 177 |
| abstract_inverted_index.This | 53 |
| abstract_inverted_index.UNet | 107 |
| abstract_inverted_index.are: | 151 |
| abstract_inverted_index.high | 171 |
| abstract_inverted_index.into | 50, 105, 156, 163 |
| abstract_inverted_index.same | 137 |
| abstract_inverted_index.show | 135 |
| abstract_inverted_index.soft | 11 |
| abstract_inverted_index.such | 26, 39 |
| abstract_inverted_index.than | 61 |
| abstract_inverted_index.that | 13 |
| abstract_inverted_index.them | 162 |
| abstract_inverted_index.this | 34 |
| abstract_inverted_index.with | 86, 111, 120 |
| abstract_inverted_index.(iii) | 166 |
| abstract_inverted_index.UNet; | 164 |
| abstract_inverted_index.gains | 169 |
| abstract_inverted_index.heavy | 176 |
| abstract_inverted_index.ideas | 104 |
| abstract_inverted_index.image | 43 |
| abstract_inverted_index.noise | 113, 172 |
| abstract_inverted_index.paper | 54 |
| abstract_inverted_index.proof | 57 |
| abstract_inverted_index.shows | 125 |
| abstract_inverted_index.these | 103 |
| abstract_inverted_index.under | 73 |
| abstract_inverted_index.where | 144 |
| abstract_inverted_index.which | 101 |
| abstract_inverted_index.while | 123 |
| abstract_inverted_index.(SOTA) | 64 |
| abstract_inverted_index.BSD500 | 133 |
| abstract_inverted_index.biases | 49 |
| abstract_inverted_index.higher | 130 |
| abstract_inverted_index.inform | 42 |
| abstract_inverted_index.models | 147 |
| abstract_inverted_index.neural | 51 |
| abstract_inverted_index.noise. | 131 |
| abstract_inverted_index.priors | 25, 70, 141 |
| abstract_inverted_index.purely | 145 |
| abstract_inverted_index.rather | 60 |
| abstract_inverted_index.signal | 17 |
| abstract_inverted_index.strong | 74 |
| abstract_inverted_index.trend, | 138 |
| abstract_inverted_index.WIPUNet | 124 |
| abstract_inverted_index.biases; | 159 |
| abstract_inverted_index.exploit | 23 |
| abstract_inverted_index.improve | 71 |
| abstract_inverted_index.margin} | 128 |
| abstract_inverted_index.modular | 157 |
| abstract_inverted_index.obscure | 14 |
| abstract_inverted_index.provide | 142 |
| abstract_inverted_index.relying | 174 |
| abstract_inverted_index.whether | 68 |
| abstract_inverted_index.without | 173 |
| abstract_inverted_index.CIFAR-10 | 110 |
| abstract_inverted_index.Gaussian | 112 |
| abstract_inverted_index.Inspired | 32 |
| abstract_inverted_index.Weighted | 94 |
| abstract_inverted_index.analogy, | 35 |
| abstract_inverted_index.collider | 4 |
| abstract_inverted_index.concept: | 59 |
| abstract_inverted_index.degrade. | 148 |
| abstract_inverted_index.particle | 2 |
| abstract_inverted_index.physical | 24 |
| abstract_inverted_index.physics, | 3 |
| abstract_inverted_index.residual | 84 |
| abstract_inverted_index.standard | 121 |
| abstract_inverted_index."pileup", | 9 |
| abstract_inverted_index.Dedicated | 20 |
| abstract_inverted_index.Denoising | 99 |
| abstract_inverted_index.Inductive | 95 |
| abstract_inverted_index.U-Network | 97 |
| abstract_inverted_index.backbone. | 108 |
| abstract_inverted_index.denoising | 44 |
| abstract_inverted_index.embedding | 46 |
| abstract_inverted_index.hierarchy | 79 |
| abstract_inverted_index.inductive | 48, 158 |
| abstract_inverted_index.interest. | 19 |
| abstract_inverted_index.introduce | 77 |
| abstract_inverted_index.locality, | 29 |
| abstract_inverted_index.stability | 143 |
| abstract_inverted_index.targeting | 62 |
| abstract_inverted_index.variants, | 91 |
| abstract_inverted_index.(WIPUNet), | 100 |
| abstract_inverted_index.baselines, | 122 |
| abstract_inverted_index.denoisers: | 82 |
| abstract_inverted_index.integrates | 102 |
| abstract_inverted_index.isolation. | 31 |
| abstract_inverted_index.machinery. | 178 |
| abstract_inverted_index.principles | 40, 155 |
| abstract_inverted_index.robustness | 72, 168 |
| abstract_inverted_index.strategies | 22 |
| abstract_inverted_index.suggesting | 139 |
| abstract_inverted_index.PU-inspired | 81, 116 |
| abstract_inverted_index.benchmarks, | 65 |
| abstract_inverted_index.competitive | 119 |
| abstract_inverted_index.corruption. | 75 |
| abstract_inverted_index.data-driven | 146 |
| abstract_inverted_index.experiments | 134 |
| abstract_inverted_index.high-energy | 1 |
| abstract_inverted_index.integrating | 161 |
| abstract_inverted_index.investigate | 37 |
| abstract_inverted_index.overlapping | 10 |
| abstract_inverted_index.subtraction | 21 |
| abstract_inverted_index.translating | 153 |
| abstract_inverted_index.conservation | 87 |
| abstract_inverted_index.constraints, | 88 |
| abstract_inverted_index.contaminated | 7 |
| abstract_inverted_index.hard-scatter | 16 |
| abstract_inverted_index.interactions | 12 |
| abstract_inverted_index.measurements | 5 |
| abstract_inverted_index.Complementary | 132 |
| abstract_inverted_index.conservation, | 28 |
| abstract_inverted_index.contributions | 150 |
| abstract_inverted_index.demonstrating | 167 |
| abstract_inverted_index.Gaussian-noise | 90 |
| abstract_inverted_index.\emph{widening | 127 |
| abstract_inverted_index.architectures. | 52 |
| abstract_inverted_index.physics-guided | 47 |
| abstract_inverted_index.physics-inspired | 69, 140 |
| abstract_inverted_index.state-of-the-art | 63 |
| abstract_inverted_index.pileup-mitigation | 154 |
| abstract_inverted_index.Pileup-physics-inspired | 96 |
| abstract_inverted_index.$σ\in\{15,25,50,75,100\}$, | 115 |
| cited_by_percentile_year | |
| corresponding_author_ids | https://openalex.org/A5080699493 |
| countries_distinct_count | 0 |
| institutions_distinct_count | 1 |
| citation_normalized_percentile |