ICMH-Net: Neural Image Compression Towards both Machine Vision and Human Vision

Author:

Liu Lei1ORCID,Hu Zhihao1ORCID,Chen Zhenghao2ORCID,Xu Dong3ORCID

Affiliation:

1. Beihang University, Beijing, China

2. The University of Sydney, Sydney, Australia

3. The University of Hong Kong, Hong Kong, Hong Kong

Funder

The Startup Funding and the Seed Funding for Basic Research for New Staff from The University of Hong Kong

The Hong Kong Jockey Club Charities Trust

UBTECH Robotics

Publisher

ACM

Reference53 articles.

1. Towards End-to-End Image Compression and Analysis with Transformers

2. Johannes Ballé , Valero Laparra , and Eero P Simoncelli . 2017 . End-to-end optimized image compression . In 5th International Conference on Learning Representations, ICLR 2017. Johannes Ballé, Valero Laparra, and Eero P Simoncelli. 2017. End-to-end optimized image compression. In 5th International Conference on Learning Representations, ICLR 2017.

3. Johannes Ballé , David Minnen , Saurabh Singh , Sung Jin Hwang , and Nick Johnston . 2018 . Variational image compression with a scale hyperprior . In International Conference on Learning Representations. Johannes Ballé, David Minnen, Saurabh Singh, Sung Jin Hwang, and Nick Johnston. 2018. Variational image compression with a scale hyperprior. In International Conference on Learning Representations.

4. Gisle Bjontegaard . 2001. Calculation of average PSNR differences between RD-curves. ITU SG16 Doc. VCEG-M33 ( 2001 ). Gisle Bjontegaard. 2001. Calculation of average PSNR differences between RD-curves. ITU SG16 Doc. VCEG-M33 (2001).

5. Exploiting Intra-Slice and Inter-Slice Redundancy for Learning-Based Lossless Volumetric Image Compression

Cited by 2 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. Towards Point Cloud Compression for Machine Perception: A Simple and Strong Baseline by Learning the Octree Depth Level Predictor;Communications in Computer and Information Science;2024

2. Neural Video Compression with Spatio-Temporal Cross-Covariance Transformers;Proceedings of the 31st ACM International Conference on Multimedia;2023-10-26

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3