# End-to-End Semantic Preservation in Text-Aware Image Compression Systems

arXiv: https://arxiv.org/abs/2503.19495 · HTML: https://mlsanity.com/paper/2503.19495/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 33 references that are in the map.
- First posted on arXiv 25 Mar 2025.

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

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Spatial Transformer Networks](https://mlsanity.com/paper/1506.02025/) (2015)
- [Variational image compression with a scale hyperprior](https://mlsanity.com/paper/1802.01436/) (2018)
- [End-to-end Optimized Image Compression](https://mlsanity.com/paper/1611.01704/) (2016)
- [An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition](https://mlsanity.com/paper/1507.05717/) (2015)
- [ELIC: Efficient Learned Image Compression with Unevenly Grouped Space-Channel Contextual Adaptive Coding](https://mlsanity.com/paper/2203.10886/) (2022)
- [Character Region Awareness for Text Detection](https://mlsanity.com/paper/1904.01941/) (2019)
- [EAST: An Efficient and Accurate Scene Text Detector](https://mlsanity.com/paper/1704.03155/) (2017)
- [Learned Image Compression with Mixed Transformer-CNN Architectures](https://mlsanity.com/paper/2303.14978/) (2023)
- [What Is Wrong With Scene Text Recognition Model Comparisons? Dataset and Model Analysis](https://mlsanity.com/paper/1904.01906/) (2019)
- [The Devil Is in the Details: Window-based Attention for Image Compression](https://mlsanity.com/paper/2203.08450/) (2022)
- [Robust Scene Text Recognition with Automatic Rectification](https://mlsanity.com/paper/1603.03915/) (2016)
- [Focusing Attention: Towards Accurate Text Recognition in Natural Images](https://mlsanity.com/paper/1709.02054/) (2017)
- [TransTIC: Transferring Transformer-based Image Compression from Human Perception to Machine Perception](https://mlsanity.com/paper/2306.05085/) (2023)
- [Single Shot Text Detector with Regional Attention](https://mlsanity.com/paper/1709.00138/) (2017)
- [Neural Data-Dependent Transform for Learned Image Compression](https://mlsanity.com/paper/2203.04963/) (2022)
- [High-Efficiency Lossy Image Coding Through Adaptive Neighborhood Information Aggregation](https://mlsanity.com/paper/2204.11448/) (2022)
- [Bridging Compressed Image Latents and Multimodal Large Language Models](https://mlsanity.com/paper/2407.19651/) (2024)
- [Transformer-based Learned Image Compression for Joint Decoding and Denoising](https://mlsanity.com/paper/2402.12888/) (2024)
- [Variable-size Symmetry-based Graph Fourier Transforms for image compression](https://mlsanity.com/paper/2411.15824/) (2024)

## Abstract (arXiv)

Traditional image compression methods aim to reconstruct images for human perception, prioritizing visual fidelity over task relevance. In contrast, Coding for Machines focuses on preserving information essential for automated understanding. Building on this principle, we present an end-to-end compression framework that retains text-specific features for Optical Character Recognition (OCR). The encoder operates at roughly half the computational cost of the OCR module, making it suitable for resource-limited devices. When on-device OCR is infeasible, images can be efficiently compressed and later decoded to recover textual content. Experiments show significant improvements in text extraction accuracy at low bitrates, even outperforming OCR on uncompressed images. We further extend this study to general-purpose encoders, exploring their capacity to preserve hidden semantics under extreme compression. Instead of optimizing for visual fidelity, we examine whether compact, visually degraded representations can retain recoverable meaning through learned enhancement and recognition modules. Results demonstrate that semantic information can persist despite severe compression, bridging text-oriented compression and general-purpose semantic preservation in machine-centered image coding.