# Learned Scalable Image Compression with Bidirectional Context Disentanglement Network

arXiv: https://arxiv.org/abs/1812.09443 · HTML: https://mlsanity.com/paper/1812.09443/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Dec 2018.

## Built on by (most cited first, 5 of 5)

- [Universal Efficient Variable-rate Neural Image Compression](https://mlsanity.com/paper/2111.11305/) (2021)
- [DeepFGS: Fine-Grained Scalable Coding for Learned Image Compression](https://mlsanity.com/paper/2412.00437/) (2024)
- [COMPASS: High-Efficiency Deep Image Compression with Arbitrary-scale Spatial Scalability](https://mlsanity.com/paper/2309.07926/) (2023)
- [DeepFGS: Fine-Grained Scalable Coding for Learned Image Compression](https://mlsanity.com/paper/2201.01173/) (2022)
- [Variable Rate Image Compression via N-Gram Context based Swin-transformer](https://mlsanity.com/paper/2510.00058/) (2025)

## Abstract (arXiv)

In this paper, we propose a learned scalable/progressive image compression scheme based on deep neural networks (DNN), named Bidirectional Context Disentanglement Network (BCD-Net). For learning hierarchical representations, we first adopt bit-plane decomposition to decompose the information coarsely before the deep-learning-based transformation. However, the information carried by different bit-planes is not only unequal in entropy but also of different importance for reconstruction. We thus take the hidden features corresponding to different bit-planes as the context and design a network topology with bidirectional flows to disentangle the contextual information for more effective compressed representations. Our proposed scheme enables us to obtain the compressed codes with scalable rates via a one-pass encoding-decoding. Experiment results demonstrate that our proposed model outperforms the state-of-the-art DNN-based scalable image compression methods in both PSNR and MS-SSIM metrics. In addition, our proposed model achieves higher performance in MS-SSIM metric than conventional scalable image codecs. Effectiveness of our technical components is also verified through sufficient ablation experiments.