Information technology — JPEG AI learning-based image coding system — Part 1: Core coding system

This document specifies an image coding technology known as JPEG AI learning-based image coding (JPEG AI) comprising an image coding technology that facilitates the compression and processing of images for both human and machine vision. The scope of the JPEG AI document is the creation of a learning-based image coding standard offering a single-stream, compact compressed domain representation, targeting both human visualization, with significant compression efficiency improvement over image coding standards in common use at equivalent subjective quality, and effective performance for image processing and computer vision tasks. The core coding system describes JPEG AI standard for the human vision reconstruction task and thus specifies the JPEG AI specifies the parsing coded stream and the image reconstruction process. Only the syntax format, semantics, and associated decoding process requirements are specified, while other matters such as pre-processing, the encoding process, system signalling and multiplexing, data loss recovery, post-processing, and video display are considered to be outside the scope of this document. This document is designed to be generic in the sense that it serves a wide range of applications, bit rates, resolutions, qualities and services. In the course of creating this document, several requirements from typical applications have been considered, necessary algorithmic elements have been developed, and these have been integrated into a single syntax. Hence, this document is designed to facilitate image data interchange among different applications and services.

Titre manque — Partie 1: Titre manque

General Information

Status
Published
Publication Date
31-Aug-2025
Current Stage
6060 - International Standard published
Start Date
01-Sep-2025
Due Date
19-Jul-2025
Completion Date
01-Sep-2025
Ref Project

Buy Standard

Standard
ISO/IEC 6048-1:2025 - Information technology — JPEG AI learning-based image coding system — Part 1: Core coding system Released:1. 09. 2025
English language
95 pages
sale 15% off
Preview
sale 15% off
Preview

Standards Content (Sample)


International
Standard
ISO/IEC 6048-1
First edition
Information technology — JPEG
2025-09
AI learning-based image coding
system —
Part 1:
Core coding system
Reference number
© ISO/IEC 2025
All rights reserved. Unless otherwise specified, or required in the context of its implementation, no part of this publication may
be reproduced or utilized otherwise in any form or by any means, electronic or mechanical, including photocopying, or posting on
the internet or an intranet, without prior written permission. Permission can be requested from either ISO at the address below
or ISO’s member body in the country of the requester.
ISO copyright office
CP 401 • Ch. de Blandonnet 8
CH-1214 Vernier, Geneva
Phone: +41 22 749 01 11
Email: copyright@iso.org
Website: www.iso.org
Published in Switzerland
© ISO/IEC 2025 – All rights reserved
ii
Foreword
ISO (the International Organization for Standardization) and IEC (the International Electrotechnical Commission)
form the specialized system for worldwide standardization. National bodies that are members of ISO or IEC
participate in the development of International Standards through technical committees established by the
respective organization to deal with particular fields of technical activity. ISO and IEC technical committees
collaborate in fields of mutual interest. Other international organizations, governmental and non-governmental, in
liaison with ISO and IEC, also take part in the work.
The procedures used to develop this document and those intended for its further maintenance are described in the
ISO/IEC Directives, Part 1. In particular, the different approval criteria needed for the different types of document
should be noted.
ISO and IEC draw attention to the possibility that the implementation of this document may involve the use of (a)
patent(s). ISO and IEC take no position concerning the evidence, validity or applicability of any claimed patent rights
in respect thereof. As of the date of publication of this document, ISO and IEC had received notice of (a) patent(s)
which may be required to implement this document. However, implementers are cautioned that this may not
represent the latest information, which may be obtained from the patent database available at www.iso.org/patents
and https://patents.iec.ch. ISO and IEC shall not be held responsible for identifying any or all such patent rights.
Any trade name used in this document is information given for the convenience of users and does not constitute an
endorsement.
For an explanation of the voluntary nature of standards, the meaning of ISO specific terms and expressions related
to conformity assessment, as well as information about ISO's adherence to the World Trade Organization (WTO)
principles in the Technical Barriers to Trade (TBT) see www.iso.org/iso/foreword.html. In the IEC, see
www.iec.ch/understanding-standards.
This document was prepared by ITU-T (as ITU-T T.840.1) and drafted in accordance with its editorial
rules, in collaboration with Joint Technical Committee ISO/IEC JTC 1, Information technology, Subcommittee
SC 29, Coding of audio, picture, multimedia and hypermedia information.
A list of all parts in the ISO/IEC 6048 series can be found on the ISO and IEC websites.
Any feedback or questions on this document should be directed to the user’s national standards body. A complete
listing of these bodies can be found at www.iso.org/members.html and www.iec.ch/national-committees.

© ISO/IEC 2025 – All rights reserved
iii
INTERNATIONAL STANDARD ISO/IEC 6048-1
RECOMMENDATION ITU-T T.840.1
Information technology – JPEG AI learning-based image coding system: Core coding system

Summary
Recommendation ITU-T T.840.1 | ISO/IEC 6048-1 specifies an image coding technology known as JPEG AI learning-
based image coding (JPEG AI) and it has been designed with multi-task goal. It facilitates the compression and processing
of images for both human and machine vision. This Recommendation | International Standard describes the JPEG AI
learning-based standard for the creation of an image from the parsed single-stream, which contains the compact compressed
domain representation, targeting both human visualization, with significant compression efficiency improvement over
image coding standards in common use at equivalent subjective quality, and effective performance for image processing
and computer vision tasks.
Core coding system describes the JPEG AI standard for the human vision reconstruction task and thus specifies the parsing
of the coded stream and the image reconstruction process.
The trainable model parameters, which are an integral part of this Recommendation | International Standard, are not
contained in the Specification due to their size. Instead, the trained model parameters are available at:
https://standards.iso.org/iso-iec/6048/-1/ed-1/en/ and https://www.itu.int/myworkspace/#/t-signals/vectors?val=40 (see
subclause 18.2).
This Recommendation | International Standard was developed collaboratively with ISO/IEC JTC 1/SC 29, and corresponds
with ISO/IEC 6048-1 as common text.

*
History
Edition Recommendation Approval Study Group Unique ID
1.0 ITU-T T.840.1 2025-03-16 21 11.1002/1000/16265

Keywords
Coding, compression, decoding, human vision, image, machine vision, neural network.

_______________
*
To access the Recommendation, type the URL https://handle.itu.int/ in the address field of your web
browser, followed by the Recommendation's unique ID.
Rec. ITU-T T.840.1 (03/2025)
© ISO/IEC 2025 – All rights reserved
v
FOREWORD
The International Telecommunication Union (ITU) is the United Nations specialized agency in the field of
telecommunications, and information and communication technologies (ICTs). The ITU Telecommunication
Standardization Sector (ITU-T) is a permanent organ of ITU. ITU-T is responsible for studying technical,
operating and tariff questions and issuing Recommendations on them with a view to standardizing
telecommunications on a worldwide basis.
The World Telecommunication Standardization Assembly (WTSA), which meets every four years, establishes
the topics for study by the ITU-T study groups which, in turn, produce Recommendations on these topics.
The approval of ITU-T Recommendations is covered by the procedure laid down in WTSA Resolution 1.
In some areas of information technology which fall within ITU-T's purview, the necessary standards are
prepared on a collaborative basis with ISO and IEC.

NOTE
In this Recommendation, the expression "Administration" is used for conciseness to indicate both a
telecommunication administration and a recognized operating agency.
Compliance with this Recommendation is voluntary. However, the Recommendation may contain certain
mandatory provisions (to ensure, e.g., interoperability or applicability) and compliance with the
Recommendation is achieved when all of these mandatory provisions are met. The words "shall" or some other
obligatory language such as "must" and the negative equivalents are used to express requirements. The use of
such words does not suggest that compliance with the Recommendation is required of any party.

INTELLECTUAL PROPERTY RIGHTS
ITU draws attention to the possibility that the practice or implementation of this Recommendation may involve
the use of a claimed Intellectual Property Right. ITU takes no position concerning the evidence, validity or
applicability of claimed Intellectual Property Rights, whether asserted by ITU members or others outside of
the Recommendation development process.
As of the date of approval of this Recommendation, ITU had received notice of intellectual property, protected
by patents/software copyrights, which may be required to implement this Recommendation. However,
implementers are cautioned that this may not represent the latest information and are therefore strongly urged
to consult the appropriate ITU-T databases available via the ITU-T website at https://www.itu.int/ITU-T/ipr/.

 ITU 2025
All rights reserved. No part of this publication may be reproduced, by any means whatsoever, without the prior
written permission of ITU.
Rec. ITU-T T.840.1 (03/2025)
© ISO/IEC 2025 – All rights reserved
vi
CONTENTS
Page
1 Scope . 1
2 Normative references . 1
2.1 Identical Recommendations | International Standards . 1
2.2 Paired Recommendations | International Standards equivalent in technical content . 1
2.3 Additional references . 1
3 Definitions . 1
4 Abbreviations . 3
5 Conventions . 4
5.1 General . 4
5.2 Arithmetic operators . 4
5.3 Logical operators . 5
5.4 Relational operators . 5
5.5 Bit-wise operators . 5
5.6 Assignment operators . 5
5.7 Range notation . 6
5.8 Mathematical functions . 6
5.9 Order of operation precedence . 6
5.10 Variables, syntax elements and tables . 7
5.11 Text description of logical operations . 8
5.12 Processes . 9
6 Image representation, tensor operations and neural network . 9
6.1 Image representation . 9
6.2 Tensor operations and neural network design elements . 9
6.2.1 Average pooling 8 . 9
6.2.2 Batch normalization . 9
6.2.3 Bicubic upsampling . 10
6.2.4 Concatenation of two tensors . 10
6.2.5 Concatenation of three tensors . 10
6.2.6 Convolution layer . 10
6.2.7 Convolution-based attention block . 10
6.2.8 Cropping layer. 11
6.2.9 Deinteger function . 11
6.2.10 Downsampling layer . 11
6.2.11 Downshuffle operation . 11
6.2.12 Grouped convolution layer . 12
6.2.13 Layer normalization . 12
6.2.14 Latent combine block . 12
6.2.15 Lightweight residual block . 13
6.2.16 Matrix transpose . 13
6.2.17 Matrix multiplication . 13
6.2.18 Multiplication of tensors by a constant . 13
6.2.19 Nearest neighbour downsampling . 13
6.2.20 Padding layer . 14
6.2.21 Per element absolute value .
...

Questions, Comments and Discussion

Ask us and Technical Secretary will try to provide an answer. You can facilitate discussion about the standard in here.