# Multistage Spatial Context Models for Learned Image Compression

arXiv: https://arxiv.org/abs/2302.09263 · HTML: https://mlsanity.com/paper/2302.09263/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 18 references that are in the map.
- First posted on arXiv 18 Feb 2023.

## Builds on (most cited first, 13 of 13)

- [Variational image compression with a scale hyperprior](https://mlsanity.com/paper/1802.01436/) (2018)
- [Joint Autoregressive and Hierarchical Priors for Learned Image Compression](https://mlsanity.com/paper/1809.02736/) (2018)
- [Learned Image Compression with Discretized Gaussian Mixture Likelihoods and Attention Modules](https://mlsanity.com/paper/2001.01568/) (2020)
- [The Open Images Dataset V4: Unified image classification, object detection, and visual relationship detection at scale](https://mlsanity.com/paper/1811.00982/) (2018)
- [ELIC: Efficient Learned Image Compression with Unevenly Grouped Space-Channel Contextual Adaptive Coding](https://mlsanity.com/paper/2203.10886/) (2022)
- [CompressAI: a PyTorch library and evaluation platform for end-to-end compression research](https://mlsanity.com/paper/2011.03029/) (2020)
- [Channel-wise Autoregressive Entropy Models for Learned Image Compression](https://mlsanity.com/paper/2007.08739/) (2020)
- [Checkerboard Context Model for Efficient Learned Image Compression](https://mlsanity.com/paper/2103.15306/) (2021)
- [Variable Rate Deep Image Compression With a Conditional Autoencoder](https://mlsanity.com/paper/1909.04802/) (2019)
- [Entroformer: A Transformer-based Entropy Model for Learned Image Compression](https://mlsanity.com/paper/2202.05492/) (2022)
- [Contextformer: A Transformer with Spatio-Channel Attention for Context Modeling in Learned Image Compression](https://mlsanity.com/paper/2203.02452/) (2022)
- [Efficient and Effective Context-Based Convolutional Entropy Modeling for Image Compression](https://mlsanity.com/paper/1906.10057/) (2019)
- [High-Efficiency Lossy Image Coding Through Adaptive Neighborhood Information Aggregation](https://mlsanity.com/paper/2204.11448/) (2022)

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

- [Learned Image Compression with Mixed Transformer-CNN Architectures](https://mlsanity.com/paper/2303.14978/) (2023)
- [MLIC++: Linear Complexity Multi-Reference Entropy Modeling for Learned Image Compression](https://mlsanity.com/paper/2307.15421/) (2023)
- [Causal Context Adjustment Loss for Learned Image Compression](https://mlsanity.com/paper/2410.04847/) (2024)
- [Channel-wise Feature Decorrelation for Enhanced Learned Image Compression](https://mlsanity.com/paper/2403.10936/) (2024)
- [Dynamic Kernel-Based Adaptive Spatial Aggregation for Learned Image Compression](https://mlsanity.com/paper/2308.08723/) (2023)

## Abstract (arXiv)

Recent state-of-the-art Learned Image Compression methods feature spatial context models, achieving great rate-distortion improvements over hyperprior methods. However, the autoregressive context model requires serial decoding, limiting runtime performance. The Checkerboard context model allows parallel decoding at a cost of reduced RD performance. We present a series of multistage spatial context models allowing both fast decoding and better RD performance. We split the latent space into square patches and decode serially within each patch while different patches are decoded in parallel. The proposed method features a comparable decoding speed to Checkerboard while reaching the RD performance of Autoregressive and even also outperforming Autoregressive. Inside each patch, the decoding order must be carefully decided as a bad order negatively impacts performance; therefore, we also propose a decoding order optimization algorithm.