TreeNet: A Light Weight Model for Low Bitrate Image Compression
This work addresses the problem of high computational costs for widespread adoption of learning-based image compression, presenting an incremental improvement with specific gains in efficiency and performance.
The paper tackles the challenge of computational complexity in learning-based image compression by proposing TreeNet, a lightweight model that achieves an average 4.83% improvement in BD-rate over JPEG AI at low bitrates while reducing model complexity by 87.82%.
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.