期刊
MULTIMEDIA MODELING, MMM 2018, PT II
卷 10705, 期 -, 页码 61-72出版社
SPRINGER INTERNATIONAL PUBLISHING AG
DOI: 10.1007/978-3-319-73600-6_6
关键词
Convolutional neural network (CNN); Discrete cosine transform (DCT); Rate-distortion optimization; Transform
类别
资金
- Natural Science Foundation of China (NSFC) [61772483, 61390512, 61425026]
- Fundamental Research Funds for the Central Universities [WK3490000001]
This paper presents a block transform for image compression, where the transform is inspired by discrete cosine transform (DCT) but achieved by training convolutional neural network (CNN) models. Specifically, we adopt the combination of convolution, nonlinear mapping, and linear transform to form a non-linear transform as well as a non-linear inverse transform. The transform, quantization, and inverse transform are jointly trained to achieve the overall rate-distortion optimization. For the training purpose, we propose to estimate the rate by the l(1)-norm of the quantized coefficients. We also explore different combinations of linear/non-linear transform and inverse transform. Experimental results show that our proposed CNN-based transform achieves higher compression efficiency than fixed DCT, and also outperforms JPEG significantly at low bit rates.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据