End-to-End RGB-IR Joint Image Compression With Channel-wise Cross-modality Entropy Model Article Swipe

PDF

Haofeng Wang , Fangtao Zhou , Qi Zhang , Zeyuan Chen , Enxu Zhang , Xiaofeng Huang ·

YOU? · · 2025 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2506.21851

RGB-IR(RGB-Infrared) image pairs are frequently applied simultaneously in various applications like intelligent surveillance. However, as the number of modalities increases, the required data storage and transmission costs also double. Therefore, efficient RGB-IR data compression is essential. This work proposes a joint compression framework for RGB-IR image pair. Specifically, to fully utilize cross-modality prior information for accurate context probability modeling within and between modalities, we propose a Channel-wise Cross-modality Entropy Model (CCEM). Among CCEM, a Low-frequency Context Extraction Block (LCEB) and a Low-frequency Context Fusion Block (LCFB) are designed for extracting and aggregating the global low-frequency information from both modalities, which assist the model in predicting entropy parameters more accurately. Experimental results demonstrate that our approach outperforms existing RGB-IR image pair and single-modality compression methods on LLVIP and KAIST datasets. For instance, the proposed framework achieves a 23.1% bit rate saving on LLVIP dataset compared to the state-of-the-art RGB-IR image codec presented at CVPR 2022.

Related Topics

Maya Joint

Joint Comprehensive Plan Of Action

Chairman Of The Joint Chiefs Of Staff

Joint Direct Attack Munition

United States Withdrawal From The Joint Comprehensive Plan Of Action

Joint Strike Missile

Joint Terminal Attack Controller

Joint Light Tactical Vehicle

Agm-154 Joint Standoff Weapon

Joint Security Area

Joint Security Area (Film)

Joint Entrance Examination – Advanced

Concepts

No concepts available.

Metadata

Type: preprint
Language: en
Landing Page: http://arxiv.org/abs/2506.21851
PDF: https://arxiv.org/pdf/2506.21851
OA Status: green
OpenAlex ID: https://openalex.org/W4416260482

All OpenAlex metadata

Raw OpenAlex JSON

OpenAlex ID: https://openalex.org/W4416260482

Canonical identifier for this work in OpenAlex
DOI: https://doi.org/10.48550/arxiv.2506.21851

Digital Object Identifier
Title: End-to-End RGB-IR Joint Image Compression With Channel-wise Cross-modality Entropy Model

Work title
Type: preprint

OpenAlex work type
Language: en

Primary language
Publication year: 2025

Year of publication
Publication date: 2025-06-27

Full publication date if available
Authors: Haofeng Wang, Fangtao Zhou, Qi Zhang, Zeyuan Chen, Enxu Zhang, Xiaofeng Huang

List of authors in order
Landing page: https://arxiv.org/abs/2506.21851

Publisher landing page
PDF URL: https://arxiv.org/pdf/2506.21851

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/2506.21851

Direct OA link when available
Cited by: 0

Total citation count in OpenAlex

Full payload

id	https://openalex.org/W4416260482
doi	https://doi.org/10.48550/arxiv.2506.21851
ids.doi	https://doi.org/10.48550/arxiv.2506.21851
ids.openalex	https://openalex.org/W4416260482
fwci
type	preprint
title	End-to-End RGB-IR Joint Image Compression With Channel-wise Cross-modality Entropy Model
biblio.issue
biblio.volume
biblio.last_page
biblio.first_page
is_xpac	False
apc_list
apc_paid
language	en
locations[0].id	pmh:oai:arXiv.org:2506.21851
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/2506.21851
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/2506.21851
locations[1].id	doi:10.48550/arxiv.2506.21851
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.2506.21851
indexed_in	arxiv, datacite
authorships[0].author.id	https://openalex.org/A5101946477
authorships[0].author.orcid	https://orcid.org/0000-0002-5865-263X
authorships[0].author.display_name	Haofeng Wang
authorships[0].author_position	first
authorships[0].raw_author_name	Wang, Haofeng
authorships[0].is_corresponding	False
authorships[1].author.id	https://openalex.org/A5112977554
authorships[1].author.orcid
authorships[1].author.display_name	Fangtao Zhou
authorships[1].author_position	middle
authorships[1].raw_author_name	Zhou, Fangtao
authorships[1].is_corresponding	False
authorships[2].author.id	https://openalex.org/A5100784844
authorships[2].author.orcid	https://orcid.org/0000-0002-1037-1361
authorships[2].author.display_name	Qi Zhang
authorships[2].author_position	middle
authorships[2].raw_author_name	Zhang, Qi
authorships[2].is_corresponding	False
authorships[3].author.id	https://openalex.org/A5100313717
authorships[3].author.orcid	https://orcid.org/0009-0008-4504-7108
authorships[3].author.display_name	Zeyuan Chen
authorships[3].author_position	middle
authorships[3].raw_author_name	Chen, Zeyuan
authorships[3].is_corresponding	False
authorships[4].author.id	https://openalex.org/A5058091073
authorships[4].author.orcid
authorships[4].author.display_name	Enxu Zhang
authorships[4].author_position	middle
authorships[4].raw_author_name	Zhang, Enci
authorships[4].is_corresponding	False
authorships[5].author.id	https://openalex.org/A5042072125
authorships[5].author.orcid	https://orcid.org/0000-0002-2082-5742
authorships[5].author.display_name	Xiaofeng Huang
authorships[5].author_position	middle
authorships[5].raw_author_name	Huang, Xiaofeng
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/2506.21851
open_access.oa_status	green
open_access.any_repository_has_fulltext	False
created_date	2025-10-10T00:00:00
display_name	End-to-End RGB-IR Joint Image Compression With Channel-wise Cross-modality Entropy Model
has_fulltext	False
is_retracted	False
updated_date	2025-11-28T09:37:08.065477
primary_topic
cited_by_count	0
locations_count	2
best_oa_location.id	pmh:oai:arXiv.org:2506.21851
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/2506.21851
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/2506.21851
primary_location.id	pmh:oai:arXiv.org:2506.21851
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/2506.21851
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/2506.21851
publication_date	2025-06-27
publication_year	2025
referenced_works_count	0
abstract_inverted_index.a	39, 65, 73, 80, 135
abstract_inverted_index.as	14
abstract_inverted_index.at	151
abstract_inverted_index.in	7, 103
abstract_inverted_index.is	34
abstract_inverted_index.of	17
abstract_inverted_index.on	124, 140
abstract_inverted_index.to	48, 144
abstract_inverted_index.we	63
abstract_inverted_index.For	129
abstract_inverted_index.and	24, 60, 79, 90, 120, 126
abstract_inverted_index.are	3, 86
abstract_inverted_index.bit	137
abstract_inverted_index.for	43, 54, 88
abstract_inverted_index.our	113
abstract_inverted_index.the	15, 20, 92, 101, 131, 145
abstract_inverted_index.CVPR	152
abstract_inverted_index.This	36
abstract_inverted_index.also	27
abstract_inverted_index.both	97
abstract_inverted_index.data	22, 32
abstract_inverted_index.from	96
abstract_inverted_index.like	10
abstract_inverted_index.more	107
abstract_inverted_index.pair	119
abstract_inverted_index.rate	138
abstract_inverted_index.that	112
abstract_inverted_index.work	37
abstract_inverted_index.2022.	153
abstract_inverted_index.23.1%	136
abstract_inverted_index.Among	71
abstract_inverted_index.Block	77, 84
abstract_inverted_index.CCEM,	72
abstract_inverted_index.KAIST	127
abstract_inverted_index.LLVIP	125, 141
abstract_inverted_index.Model	69
abstract_inverted_index.codec	149
abstract_inverted_index.costs	26
abstract_inverted_index.fully	49
abstract_inverted_index.image	1, 45, 118, 148
abstract_inverted_index.joint	40
abstract_inverted_index.model	102
abstract_inverted_index.pair.	46
abstract_inverted_index.pairs	2
abstract_inverted_index.prior	52
abstract_inverted_index.which	99
abstract_inverted_index.(LCEB)	78
abstract_inverted_index.(LCFB)	85
abstract_inverted_index.Fusion	83
abstract_inverted_index.RGB-IR	31, 44, 117, 147
abstract_inverted_index.assist	100
abstract_inverted_index.global	93
abstract_inverted_index.number	16
abstract_inverted_index.saving	139
abstract_inverted_index.within	59
abstract_inverted_index.(CCEM).	70
abstract_inverted_index.Context	75, 82
abstract_inverted_index.Entropy	68
abstract_inverted_index.applied	5
abstract_inverted_index.between	61
abstract_inverted_index.context	56
abstract_inverted_index.dataset	142
abstract_inverted_index.double.	28
abstract_inverted_index.entropy	105
abstract_inverted_index.methods	123
abstract_inverted_index.propose	64
abstract_inverted_index.results	110
abstract_inverted_index.storage	23
abstract_inverted_index.utilize	50
abstract_inverted_index.various	8
abstract_inverted_index.However,	13
abstract_inverted_index.accurate	55
abstract_inverted_index.achieves	134
abstract_inverted_index.approach	114
abstract_inverted_index.compared	143
abstract_inverted_index.designed	87
abstract_inverted_index.existing	116
abstract_inverted_index.modeling	58
abstract_inverted_index.proposed	132
abstract_inverted_index.proposes	38
abstract_inverted_index.required	21
abstract_inverted_index.datasets.	128
abstract_inverted_index.efficient	30
abstract_inverted_index.framework	42, 133
abstract_inverted_index.instance,	130
abstract_inverted_index.presented	150
abstract_inverted_index.Extraction	76
abstract_inverted_index.Therefore,	29
abstract_inverted_index.essential.	35
abstract_inverted_index.extracting	89
abstract_inverted_index.frequently	4
abstract_inverted_index.increases,	19
abstract_inverted_index.modalities	18
abstract_inverted_index.parameters	106
abstract_inverted_index.predicting	104
abstract_inverted_index.accurately.	108
abstract_inverted_index.aggregating	91
abstract_inverted_index.compression	33, 41, 122
abstract_inverted_index.demonstrate	111
abstract_inverted_index.information	53, 95
abstract_inverted_index.intelligent	11
abstract_inverted_index.modalities,	62, 98
abstract_inverted_index.outperforms	115
abstract_inverted_index.probability	57
abstract_inverted_index.Channel-wise	66
abstract_inverted_index.Experimental	109
abstract_inverted_index.applications	9
abstract_inverted_index.transmission	25
abstract_inverted_index.Low-frequency	74, 81
abstract_inverted_index.Specifically,	47
abstract_inverted_index.low-frequency	94
abstract_inverted_index.surveillance.	12
abstract_inverted_index.Cross-modality	67
abstract_inverted_index.cross-modality	51
abstract_inverted_index.simultaneously	6
abstract_inverted_index.single-modality	121
abstract_inverted_index.state-of-the-art	146
abstract_inverted_index.RGB-IR(RGB-Infrared)	0
cited_by_percentile_year
countries_distinct_count	0
institutions_distinct_count	6
citation_normalized_percentile