Generative Visual Compression: A Review

Bolin Chen; Shanzhi Yin; Peilin Chen; Shiqi Wang; Yan Ye

doi:10.1109/ICIP51287.2024.10647820

Generative Visual Compression: A Review

Department of Computer Science

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

12 Citations (Scopus)

Abstract

Artificial Intelligence Generated Content (AIGC) is leading a new technical revolution for the acquisition of digital content and impelling the progress of visual compression towards competitive performance gains and diverse functionalities over traditional codecs. This paper provides a thorough review on the recent advances of generative visual compression, illustrating great potentials and promising applications in ultra-low bitrate communication, user-specified reconstruction/filtering, and intelligent machine analysis. In particular, we review the visual data compression methodologies with deep generative models, and summarize how compact representation and high-quality reconstruction could be actualized via generative techniques. In addition, we generalize related generative compression technologies for machine vision with different-domain analysis. Finally, we discuss the fundamental challenges on generative visual compression techniques and envision their future research directions. © 2024 IEEE.

Original language	English
Title of host publication	2024 IEEE International Conference on Image Processing (ICIP) - Proceedings
Pages	3709-3715
ISBN (Electronic)	979-8-3503-4939-9
DOIs	https://doi.org/10.1109/ICIP51287.2024.10647820
Publication status	Published - 2024
Event	31st IEEE International Conference on Image Processing (ICIP 2024): Trustworthy Visual Data Processing - Abu Dhabi, United Arab Emirates Duration: 27 Oct 2024 → 30 Oct 2024 https://2024.ieeeicip.org/ https://ieeexplore.ieee.org/xpl/conhome/10647221/proceeding

Publication series

Name
ISSN (Print)	1522-4880
ISSN (Electronic)	2381-8549

Conference

Conference	31st IEEE International Conference on Image Processing (ICIP 2024)
Abbreviated title	IEEE ICIP 2024
Place	United Arab Emirates
City	Abu Dhabi
Period	27/10/24 → 30/10/24
Internet address	https://2024.ieeeicip.org/ https://ieeexplore.ieee.org/xpl/conhome/10647221/proceeding

Bibliographical note

Information for this record is supplemented by the author(s) concerned.

Funding

This work was supported in part by the General Research Fund of the Research Grant Council of Hong Kong under 11203220, in part by CityU Applied Research Grant 9667255, and in part by the Alibaba Innovative Research.

Research Keywords

Visual data compression
deep generative models
intelligent coding/analytics

RGC Funding Information

RGC-funded

Access Output

10.1109/ICIP51287.2024.10647820

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

GRF: Towards Smart Visual Sensor Data Representation with Intelligent Sensing in the Internet of Video Things
WANG, S. (Principal Investigator / Project Coordinator), Huang, T. (Co-Investigator) & XUE, C. J. (Co-Investigator)
1/01/21 → 23/06/25
Project: Research

Cite this

@inproceedings{33bf7811f1184f6493fb36da3de8b483,

title = "Generative Visual Compression: A Review",

abstract = "Artificial Intelligence Generated Content (AIGC) is leading a new technical revolution for the acquisition of digital content and impelling the progress of visual compression towards competitive performance gains and diverse functionalities over traditional codecs. This paper provides a thorough review on the recent advances of generative visual compression, illustrating great potentials and promising applications in ultra-low bitrate communication, user-specified reconstruction/filtering, and intelligent machine analysis. In particular, we review the visual data compression methodologies with deep generative models, and summarize how compact representation and high-quality reconstruction could be actualized via generative techniques. In addition, we generalize related generative compression technologies for machine vision with different-domain analysis. Finally, we discuss the fundamental challenges on generative visual compression techniques and envision their future research directions. {\textcopyright} 2024 IEEE.",

keywords = "Visual data compression, deep generative models, intelligent coding/analytics",

author = "Bolin Chen and Shanzhi Yin and Peilin Chen and Shiqi Wang and Yan Ye",

note = "Information for this record is supplemented by the author(s) concerned.; 31st IEEE International Conference on Image Processing (ICIP 2024) : Trustworthy Visual Data Processing, IEEE ICIP 2024 ; Conference date: 27-10-2024 Through 30-10-2024",

year = "2024",

doi = "10.1109/ICIP51287.2024.10647820",

language = "English",

isbn = "979-8-3503-4940-5",

pages = "3709--3715",

booktitle = "2024 IEEE International Conference on Image Processing (ICIP) - Proceedings",

url = "https://2024.ieeeicip.org/, https://ieeexplore.ieee.org/xpl/conhome/10647221/proceeding",

}

TY - GEN

T1 - Generative Visual Compression

T2 - 31st IEEE International Conference on Image Processing (ICIP 2024)

AU - Chen, Bolin

AU - Yin, Shanzhi

AU - Chen, Peilin

AU - Wang, Shiqi

AU - Ye, Yan

N1 - Information for this record is supplemented by the author(s) concerned.

PY - 2024

Y1 - 2024

N2 - Artificial Intelligence Generated Content (AIGC) is leading a new technical revolution for the acquisition of digital content and impelling the progress of visual compression towards competitive performance gains and diverse functionalities over traditional codecs. This paper provides a thorough review on the recent advances of generative visual compression, illustrating great potentials and promising applications in ultra-low bitrate communication, user-specified reconstruction/filtering, and intelligent machine analysis. In particular, we review the visual data compression methodologies with deep generative models, and summarize how compact representation and high-quality reconstruction could be actualized via generative techniques. In addition, we generalize related generative compression technologies for machine vision with different-domain analysis. Finally, we discuss the fundamental challenges on generative visual compression techniques and envision their future research directions. © 2024 IEEE.

AB - Artificial Intelligence Generated Content (AIGC) is leading a new technical revolution for the acquisition of digital content and impelling the progress of visual compression towards competitive performance gains and diverse functionalities over traditional codecs. This paper provides a thorough review on the recent advances of generative visual compression, illustrating great potentials and promising applications in ultra-low bitrate communication, user-specified reconstruction/filtering, and intelligent machine analysis. In particular, we review the visual data compression methodologies with deep generative models, and summarize how compact representation and high-quality reconstruction could be actualized via generative techniques. In addition, we generalize related generative compression technologies for machine vision with different-domain analysis. Finally, we discuss the fundamental challenges on generative visual compression techniques and envision their future research directions. © 2024 IEEE.

KW - Visual data compression

KW - deep generative models

KW - intelligent coding/analytics

U2 - 10.1109/ICIP51287.2024.10647820

DO - 10.1109/ICIP51287.2024.10647820

M3 - RGC 32 - Refereed conference paper (with host publication)

SN - 979-8-3503-4940-5

SP - 3709

EP - 3715

BT - 2024 IEEE International Conference on Image Processing (ICIP) - Proceedings

Y2 - 27 October 2024 through 30 October 2024

ER -

Generative Visual Compression: A Review

Abstract

Publication series

Conference

Bibliographical note

Funding

Research Keywords

RGC Funding Information

Access Output

Other Access Options

Permanent Link

Fingerprint

Projects

GRF: Towards Smart Visual Sensor Data Representation with Intelligent Sensing in the Internet of Video Things

Cite this