SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1906.10057 · 2019

Efficient and Effective Context-Based Convolutional Entropy Modeling for Image Compression

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

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 then jointly optimize the CCN-based entropy model along with analysis and synthesis transforms for rate-distortion performance. Experiments on the Kodak and Tecnick datasets show that our methods powered by the proposed CCNs generally achieve comparable compression performance to the state-of-the-art while being much faster.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("1906.10057")
get_code_for_paper("1906.10057")
have("1906.10057")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/1906.10057.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/1906.10057.svg)](https://syntology.ai/paper/1906.10057)

Connect an agent — have() is free.