# 3-D Context Entropy Model for Improved Practical Image Compression

arXiv: https://arxiv.org/abs/2004.08273 · HTML: https://mlsanity.com/paper/2004.08273/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Apr 2020.

## Built on by (most cited first, 11 of 11)

- [Enhanced Invertible Encoding for Learned Image Compression](https://mlsanity.com/paper/2108.03690/) (2021)
- [Soft then Hard: Rethinking the Quantization in Neural Image Compression](https://mlsanity.com/paper/2104.05168/) (2021)
- [Learning Scalable ℓ_∞-constrained Near-lossless Image Compression via Joint Lossy Image and Residual Compression](https://mlsanity.com/paper/2103.17015/) (2021)
- [Multi-Modality Deep Network for Extreme Learned Image Compression](https://mlsanity.com/paper/2304.13583/) (2023)
- [Optimizing Image Compression via Joint Learning with Denoising](https://mlsanity.com/paper/2207.10869/) (2022)
- [Online Meta Adaptation for Variable-Rate Learned Image Compression](https://mlsanity.com/paper/2111.08256/) (2021)
- [Make Lossy Compression Meaningful for Low-Light Images](https://mlsanity.com/paper/2305.15030/) (2023)
- [Enhancing Learned Image Compression via Cross Window-based Attention](https://mlsanity.com/paper/2410.21144/) (2024)
- [Learned Lossless JPEG Transcoding via Joint Lossy and Residual Compression](https://mlsanity.com/paper/2208.11673/) (2022)
- [Traditional Transformation Theory Guided Model for Learned Image Compression](https://mlsanity.com/paper/2402.15744/) (2024)
- [ARCHE: Autoregressive Residual Compression with Hyperprior and Excitation](https://mlsanity.com/paper/2603.10188/) (2026)

## Abstract (arXiv)

In this paper, we present our image compression framework designed for CLIC 2020 competition. Our method is based on Variational AutoEncoder (VAE) architecture which is strengthened with residual structures. In short, we make three noteworthy improvements here. First, we propose a 3-D context entropy model which can take advantage of known latent representation in current spatial locations for better entropy estimation. Second, a light-weighted residual structure is adopted for feature learning during entropy estimation. Finally, an effective training strategy is introduced for practical adaptation with different resolutions. Experiment results indicate our image compression method achieves 0.9775 MS-SSIM on CLIC validation set and 0.9809 MS-SSIM on test set.