Enhancement of CNN-based Probability Modeling by Locally Trained Adaptive Prediction for Efficient Lossless Image Coding

被引：1

作者：

Kaji, Keisuke ^{[1
]}

Kita, Yasuyo ^{[1
]}

Matsuda, Ichiro ^{[1
]}

Itoh, Susumu ^{[1
]}

Kameda, Yusuke ^{[2
]}

机构：

[1] Tokyo Univ Sci, Fac Sci & Technol, 2641 Yamazaki, Noda, Chiba 2788510, Japan

[2] Sophia Univ, Tokyo, Japan

来源：

2022 PICTURE CODING SYMPOSIUM (PCS) | 2022年

关键词：

lossless image coding; image generative model; convolutional neural network; adaptive prediction;

D O I：

10.1109/PCS56426.2022.10018003

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

An autoregressive image generative model that estimates the conditional probability distributions of image signals pel-by-pel is a promising tool for lossless image coding. In this paper, a generative model based on a convolutional neural network (CNN) was combined with a locally trained adaptive predictor to improve its accuracy. Furthermore, sets of parameters that adjust the estimated probability distribution were numerically optimized for each image to minimize the resulting coding rate. Simulation results indicate that the proposed method improves the coding efficiency obtained by the CNN-based model for most of the tested images.

引用

页码：79 / 83

页数：5