# Block-optimized Variable Bit Rate Neural Image Compression

arXiv: https://arxiv.org/abs/1805.10887 · HTML: https://mlsanity.com/paper/1805.10887/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 May 2018.

## Built on by (most cited first, 7 of 7)

- [Overfitting for Fun and Profit: Instance-Adaptive Data Compression](https://mlsanity.com/paper/2101.08687/) (2021)
- [Reducing The Amortization Gap of Entropy Bottleneck In End-to-End Image Compression](https://mlsanity.com/paper/2209.00964/) (2022)
- [Adaptation and Attention for Neural Video Coding](https://mlsanity.com/paper/2112.08767/) (2021)
- [Substitutional Neural Image Compression](https://mlsanity.com/paper/2105.07512/) (2021)
- [Improving The Reconstruction Quality by Overfitted Decoder Bias in Neural Image Compression](https://mlsanity.com/paper/2210.04898/) (2022)
- [Robustly overfitting latents for flexible neural image compression](https://mlsanity.com/paper/2401.17789/) (2024)
- [Exploration of Learned Lifting-Based Transform Structures for Fully Scalable and Accessible Wavelet-Like Image Compression](https://mlsanity.com/paper/2402.18761/) (2024)

## Abstract (arXiv)

In this work, we propose an end-to-end block-based auto-encoder system for image compression. We introduce novel contributions to neural-network based image compression, mainly in achieving binarization simulation, variable bit rates with multiple networks, entropy-friendly representations, inference-stage code optimization and performance-improving normalization layers in the auto-encoder. We evaluate and show the incremental performance increase of each of our contributions.