Can I read Efficient and Effective Context-Based Convolutional Entropy Modeling for Image Compression on EtoBox?

Efficient and Effective Context-Based Convolutional Entropy Modeling for Image Compression by Li, Mu; Ma, Kede; You, Jane; Zhang, David; Zuo, Wangmeng is a scholarly article available to read on EtoBox.

What is Efficient and Effective Context-Based Convolutional Entropy Modeling for Image Compression about?

Precise estimation of the probabilistic structure of natural images plays an essential role in image compression. Despite the recent remarkable success of end-to-end optimized image compression, the latent codes are usually assumed to be fully statistically factorized in order to simplify entropy modeling. However, this assumption generally does not hold true and may hinder compression performance. Here we present context-based convolutional networks (CCNs) for efficient and effective entropy modeling. In particular, a 3D zigzag scanning order and a 3D code dividing technique are introduced to define proper coding contexts for parallel entropy decoding, both of which boil down to place translation-invariant binary masks on convolution filters of CCNs. We demonstrate the promise of CCNs for entropy modeling in both lossless and lossy image compression. For the former, we directly apply a CCN to the binarized representation of an image to compute the Bernoulli distribution of each code for entropy estimation. For the latter, the categorical distribution of each code is represented by a discretized mixture of Gaussian distributions, whose parameters are estimated by three CCNs. We the

Author

Li, Mu; Ma, Kede; You, Jane; Zhang, David; Zuo, Wangmeng

Published

2019

Language

EN