arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2004.04318eess.IV
收藏

基于离散高斯混合似然的低码率图像压缩

Low Bitrate Image Compression with Discretized Gaussian Mixture Likelihoods

Zhengxue Cheng, Heming Sun, Jiro Katto

摘要:

在本文中,我们提供了一个详细的描述,我们提交的方法Kattolab研讨会和挑战学习图像压缩(CLIC)2020。我们的方法主要采用离散高斯混合似然到以前的国家的最先进的学习压缩算法。此外,我们还描述了加速策略和低速率约束下的比特优化。实验结果表明,我们的方法Kattolab达到0.9761和0.9802的MS-SSIM在速率约束为0.15bpp在验证阶段和测试阶段,分别。此项目页面位于此https URL https://github.com/ZhengxueCheng/Learned-Image-Compression-with-GMM-and-Attention

英文摘要:

In this paper, we provide a detailed description on our submitted method Kattolab to Workshop and Challenge on Learned Image Compression (CLIC) 2020. Our method mainly incorporates discretized Gaussian Mixture Likelihoods to previous state-of-the-art learned compression algorithms. Besides, we also describes the acceleration strategies and bit optimization with the low-rate constraint. Experimental results have demonstrated that our approach Kattolab achieves 0.9761 and 0.9802 in terms of MS-SSIM at the rate constraint of 0.15bpp during the validation phase and test phase, respectively. This project page is at this https URL https://github.com/ZhengxueCheng/Learned-Image-Compression-with-GMM-and-Attention

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑