# Transformer-based Variable-rate Image Compression with Region-of-interest Control

arXiv: https://arxiv.org/abs/2305.10807 · HTML: https://mlsanity.com/paper/2305.10807/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 14 references that are in the map.
- First posted on arXiv 18 May 2023.

## Builds on (most cited first, 10 of 10)

- [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)
- [Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing](https://mlsanity.com/paper/2107.13586/) (2021)
- [Visual Prompt Tuning](https://mlsanity.com/paper/2203.12119/) (2022)
- [Recovering Realistic Texture in Image Super-resolution by Deep Spatial Feature Transform](https://mlsanity.com/paper/1804.02815/) (2018)
- [Asymmetric Gained Deep Image Compression With Continuous Rate Adaptation](https://mlsanity.com/paper/2003.02012/) (2020)
- [Transformer-based Image Compression](https://mlsanity.com/paper/2111.06707/) (2021)
- [A Unified End-to-End Framework for Efficient Deep Image Compression](https://mlsanity.com/paper/2002.03370/) (2020)
- [Variable-Rate Deep Image Compression through Spatially-Adaptive Feature Transform](https://mlsanity.com/paper/2108.09551/) (2021)
- [Variable Rate Deep Image Compression with Modulated Autoencoder](https://mlsanity.com/paper/1912.05526/) (2019)

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

- [SEAGULL: No-reference Image Quality Assessment for Regions of Interest via Vision-Language Instruction Tuning](https://mlsanity.com/paper/2411.10161/) (2024)
- [Customizable ROI-Based Deep Image Compression](https://mlsanity.com/paper/2507.00373/) (2025)
- [Rethinking Learned Image Compression: Context is All You Need](https://mlsanity.com/paper/2407.11590/) (2024)
- [Comp-X: On Defining an Interactive Learned Image Compression Paradigm With Expert-driven LLM Agent](https://mlsanity.com/paper/2508.15243/) (2025)
- [Variable Rate Image Compression via N-Gram Context based Swin-transformer](https://mlsanity.com/paper/2510.00058/) (2025)
- [End-to-End Image Compression with Segmentation Guided Dual Coding for Wind Turbines](https://mlsanity.com/paper/2603.29927/) (2026)
- [Region-Adaptive Generative Compression with Spatially Varying Diffusion Models](https://mlsanity.com/paper/2604.01122/) (2026)

## Abstract (arXiv)

This paper proposes a transformer-based learned image compression system. It is capable of achieving variable-rate compression with a single model while supporting the region-of-interest (ROI) functionality. Inspired by prompt tuning, we introduce prompt generation networks to condition the transformer-based autoencoder of compression. Our prompt generation networks generate content-adaptive tokens according to the input image, an ROI mask, and a rate parameter. The separation of the ROI mask and the rate parameter allows an intuitive way to achieve variable-rate and ROI coding simultaneously. Extensive experiments validate the effectiveness of our proposed method and confirm its superiority over the other competing methods.