Enhanced Standard Compatible Image Compression Framework based on Auxiliary Codec Networks

TL;DR

This paper introduces a standard-compatible image compression framework using Auxiliary Codec Networks that imitate existing codecs, enabling more effective learning of compact representations and postprocessing, leading to improved compression performance.

Contribution

The paper proposes a novel Auxiliary Codec Network approach that accurately models existing codecs, enhancing the learning process for compact representations and postprocessing in image compression.

Findings

Outperforms existing algorithms with JPEG and HEVC standards

Enables effective and optimal learning of compression components

Demonstrates significant improvement in compression efficiency

Abstract

To enhance image compression performance, recent deep neural network-based research can be divided into three categories: a learnable codec, a postprocessing network, and a compact representation network. The learnable codec has been designed for an end-to-end learning beyond the conventional compression modules. The postprocessing network increases the quality of decoded images using an example-based learning. The compact representation network is learned to reduce the capacity of an input image to reduce the bitrate while keeping the quality of the decoded image. However, these approaches are not compatible with the existing codecs or not optimal to increase the coding efficiency. Specifically, it is difficult to achieve optimal learning in the previous studies using the compact representation network, due to the inaccurate consideration of the codecs. In this paper, we propose a novel standard compatible image compression framework based on Auxiliary Codec Networks (ACNs). ACNs are designed to imitate image degradation operations of the existing codec, which delivers more accurate gradients to the compact representation network. Therefore, the compact representation and the postprocessing networks can be learned effectively and optimally. We demonstrate that our proposed framework based on JPEG and High Efficiency Video Coding (HEVC) standard substantially outperforms existing image compression algorithms in a standard compatible manner.