A Lightweight Deep Exclusion Unfolding Network for Single Image Reflection Removal Article Swipe

PDF

Junjie Huang , Tianrui Liu , Zihan Chen , Xinwang Liu , Meng Wang , Pier Luigi Dragotti ·

YOU? · · 2025 · Open Access ·

Single Image Reflection Removal (SIRR) is a canonical blind source separation problem and refers to the issue of separating a reflection-contaminated image into a transmission and a reflection image. The core challenge lies in minimizing the commonalities among different sources. Existing deep learning approaches either neglect the significance of feature interactions or rely on heuristically designed architectures. In this paper, we propose a novel Deep Exclusion unfolding Network (DExNet), a lightweight, interpretable, and effective network architecture for SIRR. DExNet is principally constructed by unfolding and parameterizing a simple iterative Sparse and Auxiliary Feature Update (i-SAFU) algorithm, which is specifically designed to solve a new model-based SIRR optimization formulation incorporating a general exclusion prior. This general exclusion prior enables the unfolded SAFU module to inherently identify and penalize commonalities between the transmission and reflection features, ensuring more accurate separation. The principled design of DExNet not only enhances its interpretability but also significantly improves its performance. Comprehensive experiments on four benchmark datasets demonstrate that DExNet achieves state-of-the-art visual and quantitative results while utilizing only approximately 8\% of the parameters required by leading methods.

Related Topics

Deep Purple

Deep Water (2022 Film)

The Deep End Of The Ocean (Film)

The Deep (1977 Film)

Deep Roy

Chernobyl Exclusion Zone

Concepts

No concepts available.

Metadata

Type: article
Language: en
Landing Page: http://arxiv.org/abs/2503.01938
PDF: https://arxiv.org/pdf/2503.01938
OA Status: green
OpenAlex ID: https://openalex.org/W4415339058

All OpenAlex metadata

Raw OpenAlex JSON

OpenAlex ID: https://openalex.org/W4415339058

Canonical identifier for this work in OpenAlex
Title: A Lightweight Deep Exclusion Unfolding Network for Single Image Reflection Removal

Work title
Type: article

OpenAlex work type
Language: en

Primary language
Publication year: 2025

Year of publication
Publication date: 2025-03-03

Full publication date if available
Authors: Junjie Huang, Tianrui Liu, Zihan Chen, Xinwang Liu, Meng Wang, Pier Luigi Dragotti

List of authors in order
Landing page: https://arxiv.org/abs/2503.01938

Publisher landing page
PDF URL: https://arxiv.org/pdf/2503.01938

Direct link to full text PDF
Open access: Yes

Whether a free full text is available
OA status: green

Open access status per OpenAlex
OA URL: https://arxiv.org/pdf/2503.01938

Direct OA link when available
Cited by: 0

Total citation count in OpenAlex

Full payload

id	https://openalex.org/W4415339058
doi
ids.openalex	https://openalex.org/W4415339058
fwci	0.0
type	article
title	A Lightweight Deep Exclusion Unfolding Network for Single Image Reflection Removal
biblio.issue
biblio.volume
biblio.last_page
biblio.first_page
topics[0].id	https://openalex.org/T11019
topics[0].field.id	https://openalex.org/fields/17
topics[0].field.display_name	Computer Science
topics[0].score	0.994700014591217
topics[0].domain.id	https://openalex.org/domains/3
topics[0].domain.display_name	Physical Sciences
topics[0].subfield.id	https://openalex.org/subfields/1707
topics[0].subfield.display_name	Computer Vision and Pattern Recognition
topics[0].display_name	Image Enhancement Techniques
topics[1].id	https://openalex.org/T10688
topics[1].field.id	https://openalex.org/fields/17
topics[1].field.display_name	Computer Science
topics[1].score	0.9771999716758728
topics[1].domain.id	https://openalex.org/domains/3
topics[1].domain.display_name	Physical Sciences
topics[1].subfield.id	https://openalex.org/subfields/1707
topics[1].subfield.display_name	Computer Vision and Pattern Recognition
topics[1].display_name	Image and Signal Denoising Methods
topics[2].id	https://openalex.org/T13114
topics[2].field.id	https://openalex.org/fields/22
topics[2].field.display_name	Engineering
topics[2].score	0.9405999779701233
topics[2].domain.id	https://openalex.org/domains/3
topics[2].domain.display_name	Physical Sciences
topics[2].subfield.id	https://openalex.org/subfields/2214
topics[2].subfield.display_name	Media Technology
topics[2].display_name	Image Processing Techniques and Applications
is_xpac	False
apc_list
apc_paid
language	en
locations[0].id	pmh:oai:arXiv.org:2503.01938
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/2503.01938
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/2503.01938
indexed_in	arxiv
authorships[0].author.id	https://openalex.org/A5037501616
authorships[0].author.orcid	https://orcid.org/0000-0003-2986-4665
authorships[0].author.display_name	Junjie Huang
authorships[0].author_position	first
authorships[0].raw_author_name	Huang, Jun-Jie
authorships[0].is_corresponding	False
authorships[1].author.id	https://openalex.org/A5102949546
authorships[1].author.orcid	https://orcid.org/0000-0001-7926-3310
authorships[1].author.display_name	Tianrui Liu
authorships[1].author_position	middle
authorships[1].raw_author_name	Liu, Tianrui
authorships[1].is_corresponding	False
authorships[2].author.id	https://openalex.org/A5100679794
authorships[2].author.orcid	https://orcid.org/0009-0007-8387-5687
authorships[2].author.display_name	Zihan Chen
authorships[2].author_position	middle
authorships[2].raw_author_name	Chen, Zihan
authorships[2].is_corresponding	False
authorships[3].author.id	https://openalex.org/A5101727888
authorships[3].author.orcid	https://orcid.org/0000-0001-9066-1475
authorships[3].author.display_name	Xinwang Liu
authorships[3].author_position	middle
authorships[3].raw_author_name	Liu, Xinwang
authorships[3].is_corresponding	False
authorships[4].author.id	https://openalex.org/A5100377147
authorships[4].author.orcid	https://orcid.org/0000-0002-3094-7735
authorships[4].author.display_name	Meng Wang
authorships[4].author_position	middle
authorships[4].raw_author_name	Wang, Meng
authorships[4].is_corresponding	False
authorships[5].author.id	https://openalex.org/A5053203917
authorships[5].author.orcid	https://orcid.org/0000-0002-6073-2807
authorships[5].author.display_name	Pier Luigi Dragotti
authorships[5].author_position	last
authorships[5].raw_author_name	Dragotti, Pier Luigi
authorships[5].is_corresponding	False
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/2503.01938
open_access.oa_status	green
open_access.any_repository_has_fulltext	False
created_date	2025-10-19T00:00:00
display_name	A Lightweight Deep Exclusion Unfolding Network for Single Image Reflection Removal
has_fulltext	False
is_retracted	False
updated_date	2025-11-06T04:12:42.849631
primary_topic.id	https://openalex.org/T11019
primary_topic.field.id	https://openalex.org/fields/17
primary_topic.field.display_name	Computer Science
primary_topic.score	0.994700014591217
primary_topic.domain.id	https://openalex.org/domains/3
primary_topic.domain.display_name	Physical Sciences
primary_topic.subfield.id	https://openalex.org/subfields/1707
primary_topic.subfield.display_name	Computer Vision and Pattern Recognition
primary_topic.display_name	Image Enhancement Techniques
cited_by_count	0
locations_count	1
best_oa_location.id	pmh:oai:arXiv.org:2503.01938
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/2503.01938
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/2503.01938
primary_location.id	pmh:oai:arXiv.org:2503.01938
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/2503.01938
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/2503.01938
publication_date	2025-03-03
publication_year	2025
referenced_works_count	0
abstract_inverted_index.a	6, 19, 23, 26, 62, 69, 86, 102, 109
abstract_inverted_index.In	57
abstract_inverted_index.by	82, 178
abstract_inverted_index.in	33
abstract_inverted_index.is	5, 79, 97
abstract_inverted_index.of	17, 48, 141, 174
abstract_inverted_index.on	53, 156
abstract_inverted_index.or	51
abstract_inverted_index.to	14, 100, 122
abstract_inverted_index.we	60
abstract_inverted_index.8\%	173
abstract_inverted_index.The	29, 138
abstract_inverted_index.and	12, 25, 72, 84, 90, 125, 131, 166
abstract_inverted_index.but	148
abstract_inverted_index.for	76
abstract_inverted_index.its	146, 152
abstract_inverted_index.new	103
abstract_inverted_index.not	143
abstract_inverted_index.the	15, 35, 46, 118, 129, 175
abstract_inverted_index.Deep	64
abstract_inverted_index.SAFU	120
abstract_inverted_index.SIRR	105
abstract_inverted_index.This	113
abstract_inverted_index.also	149
abstract_inverted_index.core	30
abstract_inverted_index.deep	41
abstract_inverted_index.four	157
abstract_inverted_index.into	22
abstract_inverted_index.lies	32
abstract_inverted_index.more	135
abstract_inverted_index.only	144, 171
abstract_inverted_index.rely	52
abstract_inverted_index.that	161
abstract_inverted_index.this	58
abstract_inverted_index.Image	1
abstract_inverted_index.SIRR.	77
abstract_inverted_index.among	37
abstract_inverted_index.blind	8
abstract_inverted_index.image	21
abstract_inverted_index.issue	16
abstract_inverted_index.novel	63
abstract_inverted_index.prior	116
abstract_inverted_index.solve	101
abstract_inverted_index.which	96
abstract_inverted_index.while	169
abstract_inverted_index.(SIRR)	4
abstract_inverted_index.DExNet	78, 142, 162
abstract_inverted_index.Single	0
abstract_inverted_index.Sparse	89
abstract_inverted_index.Update	93
abstract_inverted_index.design	140
abstract_inverted_index.either	44
abstract_inverted_index.image.	28
abstract_inverted_index.module	121
abstract_inverted_index.paper,	59
abstract_inverted_index.prior.	112
abstract_inverted_index.refers	13
abstract_inverted_index.simple	87
abstract_inverted_index.source	9
abstract_inverted_index.visual	165
abstract_inverted_index.Feature	92
abstract_inverted_index.Network	67
abstract_inverted_index.Removal	3
abstract_inverted_index.between	128
abstract_inverted_index.enables	117
abstract_inverted_index.feature	49
abstract_inverted_index.general	110, 114
abstract_inverted_index.leading	179
abstract_inverted_index.neglect	45
abstract_inverted_index.network	74
abstract_inverted_index.problem	11
abstract_inverted_index.propose	61
abstract_inverted_index.results	168
abstract_inverted_index.(i-SAFU)	94
abstract_inverted_index.Existing	40
abstract_inverted_index.accurate	136
abstract_inverted_index.achieves	163
abstract_inverted_index.datasets	159
abstract_inverted_index.designed	55, 99
abstract_inverted_index.enhances	145
abstract_inverted_index.ensuring	134
abstract_inverted_index.identify	124
abstract_inverted_index.improves	151
abstract_inverted_index.learning	42
abstract_inverted_index.methods.	180
abstract_inverted_index.penalize	126
abstract_inverted_index.required	177
abstract_inverted_index.sources.	39
abstract_inverted_index.unfolded	119
abstract_inverted_index.(DExNet),	68
abstract_inverted_index.Auxiliary	91
abstract_inverted_index.Exclusion	65
abstract_inverted_index.benchmark	158
abstract_inverted_index.canonical	7
abstract_inverted_index.challenge	31
abstract_inverted_index.different	38
abstract_inverted_index.effective	73
abstract_inverted_index.exclusion	111, 115
abstract_inverted_index.features,	133
abstract_inverted_index.iterative	88
abstract_inverted_index.unfolding	66, 83
abstract_inverted_index.utilizing	170
abstract_inverted_index.Reflection	2
abstract_inverted_index.algorithm,	95
abstract_inverted_index.approaches	43
abstract_inverted_index.inherently	123
abstract_inverted_index.minimizing	34
abstract_inverted_index.parameters	176
abstract_inverted_index.principled	139
abstract_inverted_index.reflection	27, 132
abstract_inverted_index.separating	18
abstract_inverted_index.separation	10
abstract_inverted_index.constructed	81
abstract_inverted_index.demonstrate	160
abstract_inverted_index.experiments	155
abstract_inverted_index.formulation	107
abstract_inverted_index.model-based	104
abstract_inverted_index.principally	80
abstract_inverted_index.separation.	137
abstract_inverted_index.architecture	75
abstract_inverted_index.interactions	50
abstract_inverted_index.lightweight,	70
abstract_inverted_index.optimization	106
abstract_inverted_index.performance.	153
abstract_inverted_index.quantitative	167
abstract_inverted_index.significance	47
abstract_inverted_index.specifically	98
abstract_inverted_index.transmission	24, 130
abstract_inverted_index.Comprehensive	154
abstract_inverted_index.approximately	172
abstract_inverted_index.commonalities	36, 127
abstract_inverted_index.heuristically	54
abstract_inverted_index.incorporating	108
abstract_inverted_index.significantly	150
abstract_inverted_index.architectures.	56
abstract_inverted_index.interpretable,	71
abstract_inverted_index.parameterizing	85
abstract_inverted_index.interpretability	147
abstract_inverted_index.state-of-the-art	164
abstract_inverted_index.reflection-contaminated	20
cited_by_percentile_year
countries_distinct_count	0
institutions_distinct_count	6
citation_normalized_percentile.value	0.52443825
citation_normalized_percentile.is_in_top_1_percent	False
citation_normalized_percentile.is_in_top_10_percent	False