Virtual Codec Supervised Re-Sampling Network for Image Compression

TL;DR

This paper introduces a novel image compression method using a virtual codec network to enable end-to-end training of re-sampling and decoding networks, improving efficiency and versatility over existing techniques.

Contribution

The paper proposes a virtual codec network to address non-differentiability in quantization, enabling effective end-to-end training for image compression frameworks.

Findings

Outperforms many state-of-the-art image compression methods.

Effective in both standard-compliant and deep neural network-based frameworks.

Enhances coding efficiency through re-sampling and quantization strategies.

Abstract

In this paper, we propose an image re-sampling compression method by learning virtual codec network (VCN) to resolve the non-differentiable problem of quantization function for image compression. Here, the image re-sampling not only refers to image full-resolution re-sampling but also low-resolution re-sampling. We generalize this method for standard-compliant image compression (SCIC) framework and deep neural networks based compression (DNNC) framework. Specifically, an input image is measured by re-sampling network (RSN) network to get re-sampled vectors. Then, these vectors are directly quantized in the feature space in SCIC, or discrete cosine transform coefficients of these vectors are quantized to further improve coding efficiency in DNNC. At the encoder, the quantized vectors or coefficients are losslessly compressed by arithmetic coding. At the receiver, the decoded vectors are utilized to restore input image by image decoder network (IDN). In order to train RSN network and IDN network together in an end-to-end fashion, our VCN network intimates projection from the re-sampled vectors to the IDN-decoded image. As a result, gradients from IDN network to RSN network can be approximated by VCN network's gradient. Because dimension reduction can be further achieved by quantization in some dimensional space after image re-sampling within auto-encoder architecture, we can well initialize our networks from pre-trained auto-encoder networks. Through extensive experiments and analysis, it is verified that the proposed method has more effectiveness and versatility than many state-of-the-art approaches.