IEEE Std 1857.11-2024 基于神经网络的图像编码标准

VIP免费

史蒂文 2025-03-12 110 3.15MB 159 页 16星币

侵权投诉

STANDARDS

IEEE Standard for Neural

Network-Based Image Coding

IEEE Computer Society

Developed by the

Data Compression Standards Committee

IEEE Std 1857.11™-2024

Authorized licensed use limited to: SWANSEA UNIVERSITY. Downloaded on February 08,2025 at 07:37:47 UTC from IEEE Xplore. Restrictions apply.

IEEE Std 1857.11™-2024

IEEE Standard for Neural

Network-Based Image Coding

Developed by the

Data Compression Standards Committee

of the

IEEE Computer Society

Approved 26 September 2024

IEEE SA Standards Board

Authorized licensed use limited to: SWANSEA UNIVERSITY. Downloaded on February 08,2025 at 07:37:47 UTC from IEEE Xplore. Restrictions apply.

Abstract: A set of tools is defined in this standard for efficient image coding, including tools for

encoding, for decoding, and for encapsulation. Some of the tools are based on trained neural

networks. These tools are designed to perform block partitioning, prediction, transform,

quantization, entropy coding, filtering, and so on.

Keywords: block partitioning, entropy coding, filtering, IEEE 1857.11™, image coding, neural

network, prediction, quantization, transform

•

The Institute of Electrical and Electronics Engineers, Inc.

3 Park Avenue, New York, NY 10016-5997, USA

IEEE is a registered trademark in the U.S. Patent & Trademark Office, owned by The Institute of Electrical and Electronics

Engineers, Incorporated.

PDF: ISBN 979-8-8557-1415-9 STD27455

Print: ISBN 979-8-8557-1416-6 STDPD27455

IEEE prohibits discrimination, harassment, and bullying.

For more information, visit https://www.ieee.org/about/corporate/governance/p9-26.html.

No part of this publication may be reproduced in any form, in an electronic retrieval system or otherwise, without the prior written permission

of the publisher.

Authorized licensed use limited to: SWANSEA UNIVERSITY. Downloaded on February 08,2025 at 07:37:47 UTC from IEEE Xplore. Restrictions apply.

文档加载中……请稍候！
如果长时间未打开，您也可以点击刷新试试。

下载文档到电脑，查找使用更方便

亲，本站95%以上的标准规范都面向会员免费，办理VIP会员下载更省钱，平均每篇不到2元

立即下载 VIP免费下载

摘要：

IEEE Std 1857.11-2024 是全球首个基于神经网络技术的正式图像编码国际标准，由IEEE电路与系统学会制定，旨在利用深度学习模型替代传统手工编码工具，实现比经典JPEG/JPEG 2000更高效的压缩性能。该标准定义了统一的神经网络架构、熵编码模块与率失真优化流程，支持有损与无损两种模式，并兼容主流的GPU/TPU推理框架。通过端到端训练，标准在同等主观质量下可节省约30%-50%的码率，特别适用于超高清视频监控、医学影像传输、云端图片存储等对带宽和存储敏感的场景。同时，标准内置

展开>> 收起<<

IEEE Std 1857.11-2024 基于神经网络的图像编码标准.pdf

共159页,预览4页

还剩页未读，继续阅读

声明：本文档系会员上传，若文档所含内容侵犯了您的版权或隐私，请立即通知，我们立即给予侵权申诉删除！

IEEE Std 1857.11-2024 基于神经网络的图像编码标准

相关推荐

开通VIP享超值会员特权

相关内容

热门标签

举报选择: