TreeNet: A Light Weight Model for Low Bitrate Image Compression

Panda MP, Rao Makkena P, Prativadibhayankaram S, Foessel S, Kaup A (2026)

Publication Type: Conference contribution

Publication year: 2026

Publisher: IEEE

City/Town: New York City

Pages Range: 1-5

Conference Proceedings Title: 2025 Picture Coding Symposium (PCS)

DOI: 10.1109/PCS65673.2025.11417522

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 lever-ages 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 Bjøntegaard delta bitrate 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.

Authors with CRIS profile

Srivatsa Prativadibhayankaram Lehrstuhl für Multimediakommunikation und Signalverarbeitung (LMS) Andre Kaup Lehrstuhl für Multimediakommunikation und Signalverarbeitung (LMS)

Involved external institutions

Fraunhofer-Institut für Integrierte Schaltungen (IIS) DE Germany (DE)

How to cite

APA:

Panda, M.P., Rao Makkena, P., Prativadibhayankaram, S., Foessel, S., & Kaup, A. (2025). TreeNet: A Light Weight Model for Low Bitrate Image Compression. In 2025 Picture Coding Symposium (PCS) (pp. 1-5). New York City: IEEE.

MLA:

Panda, Mahadev Prasad, et al. "TreeNet: A Light Weight Model for Low Bitrate Image Compression." Proceedings of the 2025 Picture Coding Symposium (PCS) New York City: IEEE, 2025. 1-5.

BibTeX: Download