|
Work item:
|
T.JPEG-AI-P
|
|
Subject/title:
|
Information technology - JPEG AI learning-based image coding system: Profiling
|
|
Status:
|
Under study [Issued from previous study period]
|
|
Approval process:
|
AAP
|
|
Type of work item:
|
Recommendation
|
|
Version:
|
New
|
|
Equivalent number:
|
ISO/IEC 6048-2 (Common)
|
|
Timing:
|
2025-10 (Medium priority)
|
|
Liaison:
|
ISO/IEC JTC1/SC29/WG1 (JPEG), ITU-T SG12, ITU-T/ISO/IEC JVET
|
|
Supporting members:
|
Huawei, Tencent, MIIC/CAICT (China), EPFL, Mitsubishi Electric, Deutsche Telekom
|
|
Summary:
|
JPEG AI targets a wide range of applications such as cloud storage, visual surveillance, autonomous vehicles and devices, image collection storage and management, live monitoring of visual data and media distribution. The objective is to design a coding solution that offers significant compression efficiency improvement over coding standards in common use at equivalent subjective quality and an effective compressed-domain processing for machine learning based image processing and computer vision tasks. Other key requirements include hardware/software implementation-friendly encoding and decoding, support for 8- and 10-bit depth, efficient coding of images with text and graphics and progressive decoding.
T.JPEG-AI-P corresponds to ISO/IEC 6048-2 and is to specify profiling for the ITU-T T.JPEG-AI core coding specification. It will specify subsets of the syntax and decoding processes in the T.JPEG-AI core coding specification to enable interoperability for encoders and decoders that use the specified profiles.
|
|
Comment:
|
-
|
|
Reference(s):
|
|
|
Historic references:
|
|
Contact(s):
|
|
| ITU-T A.5 justification(s): |
|
|
|
|
First registration in the WP:
2024-06-21 14:33:16
|
|
Last update:
2025-03-04 16:58:52
|
