# Variable Rate Image Compression via N-Gram Context based Swin-transformer

arXiv: https://arxiv.org/abs/2510.00058 · HTML: https://mlsanity.com/paper/2510.00058/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 26 references that are in the map.
- First posted on arXiv 28 Sep 2025.

## Builds on (most cited first, 20 of 20)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Swin Transformer V2: Scaling Up Capacity and Resolution](https://mlsanity.com/paper/2111.09883/) (2021)
- [Variational image compression with a scale hyperprior](https://mlsanity.com/paper/1802.01436/) (2018)
- [CompressAI: a PyTorch library and evaluation platform for end-to-end compression research](https://mlsanity.com/paper/2011.03029/) (2020)
- [Variable Rate Image Compression with Recurrent Neural Networks](https://mlsanity.com/paper/1511.06085/) (2015)
- [The Devil Is in the Details: Window-based Attention for Image Compression](https://mlsanity.com/paper/2203.08450/) (2022)
- [Density Modeling of Images using a Generalized Normalization Transformation](https://mlsanity.com/paper/1511.06281/) (2015)
- [Asymmetric Gained Deep Image Compression With Continuous Rate Adaptation](https://mlsanity.com/paper/2003.02012/) (2020)
- [On the approximation of functions by tanh neural networks](https://mlsanity.com/paper/2104.08938/) (2021)
- [Transformer-based Image Compression](https://mlsanity.com/paper/2111.06707/) (2021)
- [Variable-Rate Deep Image Compression through Spatially-Adaptive Feature Transform](https://mlsanity.com/paper/2108.09551/) (2021)
- [N-Gram in Swin Transformers for Efficient Lightweight Image Super-Resolution](https://mlsanity.com/paper/2211.11436/) (2022)
- [Linear Attention Modeling for Learned Image Compression](https://mlsanity.com/paper/2502.05741/) (2025)
- [QVRF: A Quantization-error-aware Variable Rate Framework for Learned Image Compression](https://mlsanity.com/paper/2303.05744/) (2023)
- [Transformer-based Variable-rate Image Compression with Region-of-interest Control](https://mlsanity.com/paper/2305.10807/) (2023)
- [Learned Scalable Image Compression with Bidirectional Context Disentanglement Network](https://mlsanity.com/paper/1812.09443/) (2018)
- [Balanced Rate-Distortion Optimization in Learned Image Compression](https://mlsanity.com/paper/2502.20161/) (2025)
- [Multi-Scale Invertible Neural Network for Wide-Range Variable-Rate Learned Image Compression](https://mlsanity.com/paper/2503.21284/) (2025)
- [Enhancing Learned Image Compression via Cross Window-based Attention](https://mlsanity.com/paper/2410.21144/) (2024)

## Abstract (arXiv)

This paper presents an N-gram context-based Swin Transformer for learned image compression. Our method achieves variable-rate compression with a single model. By incorporating N-gram context into the Swin Transformer, we overcome its limitation of neglecting larger regions during high-resolution image reconstruction due to its restricted receptive field. This enhancement expands the regions considered for pixel restoration, thereby improving the quality of high-resolution reconstructions. Our method increases context awareness across neighboring windows, leading to a -5.86% improvement in BD-Rate over existing variable-rate learned image compression techniques. Additionally, our model improves the quality of regions of interest (ROI) in images, making it particularly beneficial for object-focused applications in fields such as manufacturing and industrial vision systems.