Lossless Image Compression Using a Multi-Scale Progressive Statistical Model

TL;DR

This paper introduces a multi-scale progressive statistical model for lossless image compression that combines pixel-wise autoregressive accuracy with multi-scale efficiency, outperforming existing methods on benchmark datasets.

Contribution

The paper proposes a novel multi-scale progressive statistical model that balances compression performance and speed, improving upon state-of-the-art lossless image compression methods.

Findings

Outperforms state-of-the-art methods on benchmark datasets

Balances compression rate and inference speed effectively

Flexible pixel processing order enhances adaptability

Abstract

Lossless image compression is an important technique for image storage and transmission when information loss is not allowed. With the fast development of deep learning techniques, deep neural networks have been used in this field to achieve a higher compression rate. Methods based on pixel-wise autoregressive statistical models have shown good performance. However, the sequential processing way prevents these methods to be used in practice. Recently, multi-scale autoregressive models have been proposed to address this limitation. Multi-scale approaches can use parallel computing systems efficiently and build practical systems. Nevertheless, these approaches sacrifice compression performance in exchange for speed. In this paper, we propose a multi-scale progressive statistical model that takes advantage of the pixel-wise approach and the multi-scale approach. We developed a flexible mechanism where the processing order of the pixels can be adjusted easily. Our proposed method outperforms the state-of-the-art lossless image compression methods on two large benchmark datasets by a significant margin without degrading the inference speed dramatically.