Deep Lossy Plus Residual Coding for Lossless and Near-lossless Image Compression Article Swipe

PDF

Yuanchao Bai , Xianming Liu , Kai Wang , Xiangyang Ji , Xiaolin Wu , Wen Gao ·

YOU? · · 2022 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2209.04847

Lossless and near-lossless image compression is of paramount importance to professional users in many technical fields, such as medicine, remote sensing, precision engineering and scientific research. But despite rapidly growing research interests in learning-based image compression, no published method offers both lossless and near-lossless modes. In this paper, we propose a unified and powerful deep lossy plus residual (DLPR) coding framework for both lossless and near-lossless image compression. In the lossless mode, the DLPR coding system first performs lossy compression and then lossless coding of residuals. We solve the joint lossy and residual compression problem in the approach of VAEs, and add autoregressive context modeling of the residuals to enhance lossless compression performance. In the near-lossless mode, we quantize the original residuals to satisfy a given $\ell_\infty$ error bound, and propose a scalable near-lossless compression scheme that works for variable $\ell_\infty$ bounds instead of training multiple networks. To expedite the DLPR coding, we increase the degree of algorithm parallelization by a novel design of coding context, and accelerate the entropy coding with adaptive residual interval. Experimental results demonstrate that the DLPR coding system achieves both the state-of-the-art lossless and near-lossless image compression performance with competitive coding speed.

Related Topics

Artificial Intelligence

Theoretical Computer Science

Concepts

Lossless compression Lossy compression Lossless JPEG Computer science Adaptive coding Image compression Context-adaptive binary arithmetic coding Entropy encoding Data compression Algorithm Context-adaptive variable-length coding Tunstall coding Residual Artificial intelligence Theoretical computer science Image processing Image (mathematics)

Metadata

Type: preprint
Language: en
Landing Page: http://arxiv.org/abs/2209.04847
PDF: https://arxiv.org/pdf/2209.04847
OA Status: green
Cited By: 2
Related Works: 10
OpenAlex ID: https://openalex.org/W4295689521

All OpenAlex metadata

Raw OpenAlex JSON

OpenAlex ID: https://openalex.org/W4295689521

Canonical identifier for this work in OpenAlex
DOI: https://doi.org/10.48550/arxiv.2209.04847

Digital Object Identifier
Title: Deep Lossy Plus Residual Coding for Lossless and Near-lossless Image Compression

Work title
Type: preprint

OpenAlex work type
Language: en

Primary language
Publication year: 2022

Year of publication
Publication date: 2022-09-11

Full publication date if available
Authors: Yuanchao Bai, Xianming Liu, Kai Wang, Xiangyang Ji, Xiaolin Wu, Wen Gao

List of authors in order
Landing page: https://arxiv.org/abs/2209.04847

Publisher landing page
PDF URL: https://arxiv.org/pdf/2209.04847

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/2209.04847

Direct OA link when available
Concepts: Lossless compression, Lossy compression, Lossless JPEG, Computer science, Adaptive coding, Image compression, Context-adaptive binary arithmetic coding, Entropy encoding, Data compression, Algorithm, Context-adaptive variable-length coding, Tunstall coding, Residual, Artificial intelligence, Theoretical computer science, Image processing, Image (mathematics)

Top concepts (fields/topics) attached by OpenAlex
Cited by: 2

Total citation count in OpenAlex
Citations by year (recent): 2024: 1, 2023: 1

Per-year citation counts (last 5 years)
Related works (count): 10

Other works algorithmically related by OpenAlex

Full payload

id	https://openalex.org/W4295689521
doi	https://doi.org/10.48550/arxiv.2209.04847
ids.doi	https://doi.org/10.48550/arxiv.2209.04847
ids.openalex	https://openalex.org/W4295689521
fwci
type	preprint
title	Deep Lossy Plus Residual Coding for Lossless and Near-lossless Image Compression
biblio.issue
biblio.volume
biblio.last_page
biblio.first_page
topics[0].id	https://openalex.org/T10901
topics[0].field.id	https://openalex.org/fields/17
topics[0].field.display_name	Computer Science
topics[0].score	0.9997000098228455
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	Advanced Data Compression Techniques
topics[1].id	https://openalex.org/T11105
topics[1].field.id	https://openalex.org/fields/17
topics[1].field.display_name	Computer Science
topics[1].score	0.9991000294685364
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	Advanced Image Processing Techniques
topics[2].id	https://openalex.org/T10688
topics[2].field.id	https://openalex.org/fields/17
topics[2].field.display_name	Computer Science
topics[2].score	0.998199999332428
topics[2].domain.id	https://openalex.org/domains/3
topics[2].domain.display_name	Physical Sciences
topics[2].subfield.id	https://openalex.org/subfields/1707
topics[2].subfield.display_name	Computer Vision and Pattern Recognition
topics[2].display_name	Image and Signal Denoising Methods
is_xpac	False
apc_list
apc_paid
concepts[0].id	https://openalex.org/C81081738
concepts[0].level	3
concepts[0].score	0.9404826164245605
concepts[0].wikidata	https://www.wikidata.org/wiki/Q55542
concepts[0].display_name	Lossless compression
concepts[1].id	https://openalex.org/C165021410
concepts[1].level	2
concepts[1].score	0.9203943014144897
concepts[1].wikidata	https://www.wikidata.org/wiki/Q55564
concepts[1].display_name	Lossy compression
concepts[2].id	https://openalex.org/C8384606
concepts[2].level	5
concepts[2].score	0.6648266315460205
concepts[2].wikidata	https://www.wikidata.org/wiki/Q2190356
concepts[2].display_name	Lossless JPEG
concepts[3].id	https://openalex.org/C41008148
concepts[3].level	0
concepts[3].score	0.6299904584884644
concepts[3].wikidata	https://www.wikidata.org/wiki/Q21198
concepts[3].display_name	Computer science
concepts[4].id	https://openalex.org/C57890076
concepts[4].level	4
concepts[4].score	0.6220035552978516
concepts[4].wikidata	https://www.wikidata.org/wiki/Q4680725
concepts[4].display_name	Adaptive coding
concepts[5].id	https://openalex.org/C13481523
concepts[5].level	4
concepts[5].score	0.6216407418251038
concepts[5].wikidata	https://www.wikidata.org/wiki/Q412438
concepts[5].display_name	Image compression
concepts[6].id	https://openalex.org/C175732694
concepts[6].level	3
concepts[6].score	0.6073800325393677
concepts[6].wikidata	https://www.wikidata.org/wiki/Q1128713
concepts[6].display_name	Context-adaptive binary arithmetic coding
concepts[7].id	https://openalex.org/C1769480
concepts[7].level	3
concepts[7].score	0.5695054531097412
concepts[7].wikidata	https://www.wikidata.org/wiki/Q1345239
concepts[7].display_name	Entropy encoding
concepts[8].id	https://openalex.org/C78548338
concepts[8].level	2
concepts[8].score	0.5551034212112427
concepts[8].wikidata	https://www.wikidata.org/wiki/Q2493
concepts[8].display_name	Data compression
concepts[9].id	https://openalex.org/C11413529
concepts[9].level	1
concepts[9].score	0.5296532511711121
concepts[9].wikidata	https://www.wikidata.org/wiki/Q8366
concepts[9].display_name	Algorithm
concepts[10].id	https://openalex.org/C135534801
concepts[10].level	4
concepts[10].score	0.5104362368583679
concepts[10].wikidata	https://www.wikidata.org/wiki/Q1128721
concepts[10].display_name	Context-adaptive variable-length coding
concepts[11].id	https://openalex.org/C73231260
concepts[11].level	4
concepts[11].score	0.4692540168762207
concepts[11].wikidata	https://www.wikidata.org/wiki/Q7853376
concepts[11].display_name	Tunstall coding
concepts[12].id	https://openalex.org/C155512373
concepts[12].level	2
concepts[12].score	0.4324406683444977
concepts[12].wikidata	https://www.wikidata.org/wiki/Q287450
concepts[12].display_name	Residual
concepts[13].id	https://openalex.org/C154945302
concepts[13].level	1
concepts[13].score	0.35814017057418823
concepts[13].wikidata	https://www.wikidata.org/wiki/Q11660
concepts[13].display_name	Artificial intelligence
concepts[14].id	https://openalex.org/C80444323
concepts[14].level	1
concepts[14].score	0.3425936698913574
concepts[14].wikidata	https://www.wikidata.org/wiki/Q2878974
concepts[14].display_name	Theoretical computer science
concepts[15].id	https://openalex.org/C9417928
concepts[15].level	3
concepts[15].score	0.13013839721679688
concepts[15].wikidata	https://www.wikidata.org/wiki/Q1070689
concepts[15].display_name	Image processing
concepts[16].id	https://openalex.org/C115961682
concepts[16].level	2
concepts[16].score	0.10835567116737366
concepts[16].wikidata	https://www.wikidata.org/wiki/Q860623
concepts[16].display_name	Image (mathematics)
keywords[0].id	https://openalex.org/keywords/lossless-compression
keywords[0].score	0.9404826164245605
keywords[0].display_name	Lossless compression
keywords[1].id	https://openalex.org/keywords/lossy-compression
keywords[1].score	0.9203943014144897
keywords[1].display_name	Lossy compression
keywords[2].id	https://openalex.org/keywords/lossless-jpeg
keywords[2].score	0.6648266315460205
keywords[2].display_name	Lossless JPEG
keywords[3].id	https://openalex.org/keywords/computer-science
keywords[3].score	0.6299904584884644
keywords[3].display_name	Computer science
keywords[4].id	https://openalex.org/keywords/adaptive-coding
keywords[4].score	0.6220035552978516
keywords[4].display_name	Adaptive coding
keywords[5].id	https://openalex.org/keywords/image-compression
keywords[5].score	0.6216407418251038
keywords[5].display_name	Image compression
keywords[6].id	https://openalex.org/keywords/context-adaptive-binary-arithmetic-coding
keywords[6].score	0.6073800325393677
keywords[6].display_name	Context-adaptive binary arithmetic coding
keywords[7].id	https://openalex.org/keywords/entropy-encoding
keywords[7].score	0.5695054531097412
keywords[7].display_name	Entropy encoding
keywords[8].id	https://openalex.org/keywords/data-compression
keywords[8].score	0.5551034212112427
keywords[8].display_name	Data compression
keywords[9].id	https://openalex.org/keywords/algorithm
keywords[9].score	0.5296532511711121
keywords[9].display_name	Algorithm
keywords[10].id	https://openalex.org/keywords/context-adaptive-variable-length-coding
keywords[10].score	0.5104362368583679
keywords[10].display_name	Context-adaptive variable-length coding
keywords[11].id	https://openalex.org/keywords/tunstall-coding
keywords[11].score	0.4692540168762207
keywords[11].display_name	Tunstall coding
keywords[12].id	https://openalex.org/keywords/residual
keywords[12].score	0.4324406683444977
keywords[12].display_name	Residual
keywords[13].id	https://openalex.org/keywords/artificial-intelligence
keywords[13].score	0.35814017057418823
keywords[13].display_name	Artificial intelligence
keywords[14].id	https://openalex.org/keywords/theoretical-computer-science
keywords[14].score	0.3425936698913574
keywords[14].display_name	Theoretical computer science
keywords[15].id	https://openalex.org/keywords/image-processing
keywords[15].score	0.13013839721679688
keywords[15].display_name	Image processing
keywords[16].id	https://openalex.org/keywords/image
keywords[16].score	0.10835567116737366
keywords[16].display_name	Image (mathematics)
language	en
locations[0].id	pmh:oai:arXiv.org:2209.04847
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/2209.04847
locations[0].version	submittedVersion
locations[0].raw_type
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/2209.04847
locations[1].id	doi:10.48550/arxiv.2209.04847
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.2209.04847
indexed_in	arxiv, datacite
authorships[0].author.id	https://openalex.org/A5024093994
authorships[0].author.orcid	https://orcid.org/0000-0003-3449-6537
authorships[0].author.display_name	Yuanchao Bai
authorships[0].author_position	first
authorships[0].raw_author_name	Bai, Yuanchao
authorships[0].is_corresponding	False
authorships[1].author.id	https://openalex.org/A5100654390
authorships[1].author.orcid	https://orcid.org/0000-0002-8857-1785
authorships[1].author.display_name	Xianming Liu
authorships[1].author_position	middle
authorships[1].raw_author_name	Liu, Xianming
authorships[1].is_corresponding	False
authorships[2].author.id	https://openalex.org/A5100437036
authorships[2].author.orcid	https://orcid.org/0000-0002-6170-4744
authorships[2].author.display_name	Kai Wang
authorships[2].author_position	middle
authorships[2].raw_author_name	Wang, Kai
authorships[2].is_corresponding	False
authorships[3].author.id	https://openalex.org/A5024401174
authorships[3].author.orcid	https://orcid.org/0000-0002-7333-9975
authorships[3].author.display_name	Xiangyang Ji
authorships[3].author_position	middle
authorships[3].raw_author_name	Ji, Xiangyang
authorships[3].is_corresponding	False
authorships[4].author.id	https://openalex.org/A5101467562
authorships[4].author.orcid	https://orcid.org/0000-0002-0103-5374
authorships[4].author.display_name	Xiaolin Wu
authorships[4].author_position	middle
authorships[4].raw_author_name	Wu, Xiaolin
authorships[4].is_corresponding	False
authorships[5].author.id	https://openalex.org/A5018478553
authorships[5].author.orcid	https://orcid.org/0000-0002-8070-802X
authorships[5].author.display_name	Wen Gao
authorships[5].author_position	last
authorships[5].raw_author_name	Gao, Wen
authorships[5].is_corresponding	False
has_content.pdf	True
has_content.grobid_xml	True
is_paratext	False
open_access.is_oa	True
open_access.oa_url	https://arxiv.org/pdf/2209.04847
open_access.oa_status	green
open_access.any_repository_has_fulltext	False
created_date	2025-10-10T00:00:00
display_name	Deep Lossy Plus Residual Coding for Lossless and Near-lossless Image Compression
has_fulltext	True
is_retracted	False
updated_date	2025-11-06T06:51:31.235846
primary_topic.id	https://openalex.org/T10901
primary_topic.field.id	https://openalex.org/fields/17
primary_topic.field.display_name	Computer Science
primary_topic.score	0.9997000098228455
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	Advanced Data Compression Techniques
related_works	https://openalex.org/W3000696245, https://openalex.org/W2110189477, https://openalex.org/W2156373110, https://openalex.org/W2161727997, https://openalex.org/W2136537500, https://openalex.org/W2155733282, https://openalex.org/W2167897635, https://openalex.org/W61332197, https://openalex.org/W2015048732, https://openalex.org/W2083676471
cited_by_count	2
counts_by_year[0].year	2024
counts_by_year[0].cited_by_count	1
counts_by_year[1].year	2023
counts_by_year[1].cited_by_count	1
locations_count	2
best_oa_location.id	pmh:oai:arXiv.org:2209.04847
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/2209.04847
best_oa_location.version	submittedVersion
best_oa_location.raw_type
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/2209.04847
primary_location.id	pmh:oai:arXiv.org:2209.04847
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/2209.04847
primary_location.version	submittedVersion
primary_location.raw_type
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/2209.04847
publication_date	2022-09-11
publication_year	2022
referenced_works_count	0
abstract_inverted_index.a	50, 124, 131, 160
abstract_inverted_index.In	45, 68, 113
abstract_inverted_index.To	147
abstract_inverted_index.We	86
abstract_inverted_index.as	17
abstract_inverted_index.by	159
abstract_inverted_index.in	12, 32, 95
abstract_inverted_index.is	5
abstract_inverted_index.no	36
abstract_inverted_index.of	6, 84, 98, 105, 143, 156, 163
abstract_inverted_index.to	9, 108, 122
abstract_inverted_index.we	48, 117, 152
abstract_inverted_index.But	26
abstract_inverted_index.add	101
abstract_inverted_index.and	1, 23, 42, 52, 64, 80, 91, 100, 129, 166, 188
abstract_inverted_index.for	61, 138
abstract_inverted_index.the	69, 72, 88, 96, 106, 114, 119, 149, 154, 168, 179, 185
abstract_inverted_index.DLPR	73, 150, 180
abstract_inverted_index.both	40, 62, 184
abstract_inverted_index.deep	54
abstract_inverted_index.many	13
abstract_inverted_index.plus	56
abstract_inverted_index.such	16
abstract_inverted_index.that	136, 178
abstract_inverted_index.then	81
abstract_inverted_index.this	46
abstract_inverted_index.with	171, 193
abstract_inverted_index.VAEs,	99
abstract_inverted_index.error	127
abstract_inverted_index.first	76
abstract_inverted_index.given	125
abstract_inverted_index.image	3, 34, 66, 190
abstract_inverted_index.joint	89
abstract_inverted_index.lossy	55, 78, 90
abstract_inverted_index.mode,	71, 116
abstract_inverted_index.novel	161
abstract_inverted_index.solve	87
abstract_inverted_index.users	11
abstract_inverted_index.works	137
abstract_inverted_index.(DLPR)	58
abstract_inverted_index.bound,	128
abstract_inverted_index.bounds	141
abstract_inverted_index.coding	59, 74, 83, 164, 170, 181, 195
abstract_inverted_index.degree	155
abstract_inverted_index.design	162
abstract_inverted_index.method	38
abstract_inverted_index.modes.	44
abstract_inverted_index.offers	39
abstract_inverted_index.paper,	47
abstract_inverted_index.remote	19
abstract_inverted_index.scheme	135
abstract_inverted_index.speed.	196
abstract_inverted_index.system	75, 182
abstract_inverted_index.coding,	151
abstract_inverted_index.context	103
abstract_inverted_index.despite	27
abstract_inverted_index.enhance	109
abstract_inverted_index.entropy	169
abstract_inverted_index.fields,	15
abstract_inverted_index.growing	29
abstract_inverted_index.instead	142
abstract_inverted_index.problem	94
abstract_inverted_index.propose	49, 130
abstract_inverted_index.rapidly	28
abstract_inverted_index.results	176
abstract_inverted_index.satisfy	123
abstract_inverted_index.unified	51
abstract_inverted_index.Lossless	0
abstract_inverted_index.achieves	183
abstract_inverted_index.adaptive	172
abstract_inverted_index.approach	97
abstract_inverted_index.context,	165
abstract_inverted_index.expedite	148
abstract_inverted_index.increase	153
abstract_inverted_index.lossless	41, 63, 70, 82, 110, 187
abstract_inverted_index.modeling	104
abstract_inverted_index.multiple	145
abstract_inverted_index.original	120
abstract_inverted_index.performs	77
abstract_inverted_index.powerful	53
abstract_inverted_index.quantize	118
abstract_inverted_index.research	30
abstract_inverted_index.residual	57, 92, 173
abstract_inverted_index.scalable	132
abstract_inverted_index.sensing,	20
abstract_inverted_index.training	144
abstract_inverted_index.variable	139
abstract_inverted_index.algorithm	157
abstract_inverted_index.framework	60
abstract_inverted_index.interests	31
abstract_inverted_index.interval.	174
abstract_inverted_index.medicine,	18
abstract_inverted_index.networks.	146
abstract_inverted_index.paramount	7
abstract_inverted_index.precision	21
abstract_inverted_index.published	37
abstract_inverted_index.research.	25
abstract_inverted_index.residuals	107, 121
abstract_inverted_index.technical	14
abstract_inverted_index.accelerate	167
abstract_inverted_index.importance	8
abstract_inverted_index.residuals.	85
abstract_inverted_index.scientific	24
abstract_inverted_index.competitive	194
abstract_inverted_index.compression	4, 79, 93, 111, 134, 191
abstract_inverted_index.demonstrate	177
abstract_inverted_index.engineering	22
abstract_inverted_index.performance	192
abstract_inverted_index.Experimental	175
abstract_inverted_index.compression,	35
abstract_inverted_index.compression.	67
abstract_inverted_index.performance.	112
abstract_inverted_index.professional	10
abstract_inverted_index.$\ell_\infty$	126, 140
abstract_inverted_index.near-lossless	2, 43, 65, 115, 133, 189
abstract_inverted_index.autoregressive	102
abstract_inverted_index.learning-based	33
abstract_inverted_index.parallelization	158
abstract_inverted_index.state-of-the-art	186
cited_by_percentile_year
countries_distinct_count	0
institutions_distinct_count	6
citation_normalized_percentile