GOLLIC: Learning Global Context beyond Patches for Lossless High-Resolution Image Compression

TL;DR

This paper introduces GOLLIC, a hierarchical model that captures global context in high-resolution image compression, significantly improving lossless compression performance by modeling long-term dependencies beyond patches.

Contribution

It proposes a novel global context modeling approach using shared latent variables and a self-supervised clustering module, enhancing lossless high-resolution image compression.

Findings

Improved compression ratios over existing codecs and models.

Effective modeling of long-term dependencies in high-resolution images.

Validated on multiple benchmark datasets.

Abstract

Neural-network-based approaches recently emerged in the field of data compression and have already led to significant progress in image compression, especially in achieving a higher compression ratio. In the lossless image compression scenario, however, existing methods often struggle to learn a probability model of full-size high-resolution images due to the limitation of the computation source. The current strategy is to crop high-resolution images into multiple non-overlapping patches and process them independently. This strategy ignores long-term dependencies beyond patches, thus limiting modeling performance. To address this problem, we propose a hierarchical latent variable model with a global context to capture the long-term dependencies of high-resolution images. Besides the latent variable unique to each patch, we introduce shared latent variables between patches to construct the global context. The shared latent variables are extracted by a self-supervised clustering module inside the model's encoder. This clustering module assigns each patch the confidence that it belongs to any cluster. Later, shared latent variables are learned according to latent variables of patches and their confidence, which reflects the similarity of patches in the same cluster and benefits the global context modeling. Experimental results show that our global context model improves compression ratio compared to the engineered codecs and deep learning models on three benchmark high-resolution image datasets, DIV2K, CLIC.pro, and CLIC.mobile.