Journal
MULTIMEDIA MODELING, MMM 2018, PT II
Volume 10705, Issue -, Pages 61-72Publisher
SPRINGER INTERNATIONAL PUBLISHING AG
DOI: 10.1007/978-3-319-73600-6_6
Keywords
Convolutional neural network (CNN); Discrete cosine transform (DCT); Rate-distortion optimization; Transform
Categories
Funding
- Natural Science Foundation of China (NSFC) [61772483, 61390512, 61425026]
- Fundamental Research Funds for the Central Universities [WK3490000001]
Ask authors/readers for more resources
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.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available