TreeNet: A Light Weight Model for Low Bitrate Image Compression

TL;DR

TreeNet is a low-complexity, binary tree-structured image compression model that outperforms JPEG AI at low bitrates by significantly reducing model complexity and improving compression efficiency.

Contribution

We introduce TreeNet, a novel binary tree-based architecture with attentional feature fusion for efficient low-bitrate image compression, achieving superior performance and reduced complexity.

Findings

TreeNet improves BD-rate by 4.83% over JPEG AI at low bitrates.

Model complexity is reduced by 87.82% compared to existing methods.

Extensive ablation studies reveal key factors influencing reconstruction quality.

Abstract

Reducing computational complexity remains a critical challenge for the widespread adoption of learning-based image compression techniques. In this work, we propose TreeNet, a novel low-complexity image compression model that leverages a binary tree-structured encoder-decoder architecture to achieve efficient representation and reconstruction. We employ attentional feature fusion mechanism to effectively integrate features from multiple branches. We evaluate TreeNet on three widely used benchmark datasets and compare its performance against competing methods including JPEG AI, a recent standard in learning-based image compression. At low bitrates, TreeNet achieves an average improvement of 4.83% in BD-rate over JPEG AI, while reducing model complexity by 87.82%. Furthermore, we conduct extensive ablation studies to investigate the influence of various latent representations within TreeNet, offering deeper insights into the factors contributing to reconstruction.