# Reading in the Dark: Low-light Scene Text Recognition

arXiv: https://arxiv.org/abs/2604.23685 · HTML: https://mlsanity.com/paper/2604.23685/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 26 references that are in the map.
- First posted on arXiv 26 Apr 2026.

## Builds on (most cited first, 18 of 18)

- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [CBAM: Convolutional Block Attention Module](https://mlsanity.com/paper/1807.06521/) (2018)
- [Deep Retinex Decomposition for Low-Light Enhancement](https://mlsanity.com/paper/1808.04560/) (2018)
- [Zero-Reference Deep Curve Estimation for Low-Light Image Enhancement](https://mlsanity.com/paper/2001.06826/) (2020)
- [EnlightenGAN: Deep Light Enhancement without Paired Supervision](https://mlsanity.com/paper/1906.06972/) (2019)
- [Kindling the Darkness: A Practical Low-light Image Enhancer](https://mlsanity.com/paper/1905.04161/) (2019)
- [Retinex-inspired Unrolling with Cooperative Prior Architecture Search for Low-light Image Enhancement](https://mlsanity.com/paper/2012.05609/) (2020)
- [Generative Diffusion Prior for Unified Image Restoration and Enhancement](https://mlsanity.com/paper/2304.01247/) (2023)
- [Learning to Enhance Low-Light Image via Zero-Reference Deep Curve Estimation](https://mlsanity.com/paper/2103.00860/) (2021)
- [R2RNet: Low-light Image Enhancement via Real-low to Real-normal Network](https://mlsanity.com/paper/2106.14501/) (2021)
- [DEA-Net: Single image dehazing based on detail-enhanced convolution and content-guided attention](https://mlsanity.com/paper/2301.04805/) (2023)
- [Toward Understanding WordArt: Corner-Guided Transformer for Scene Text Recognition](https://mlsanity.com/paper/2208.00438/) (2022)
- [Blind Universal Bayesian Image Denoising with Gaussian Noise Level Learning](https://mlsanity.com/paper/1907.03029/) (2019)
- [Diffusion in the Dark: A Diffusion Model for Low-Light Text Recognition](https://mlsanity.com/paper/2303.04291/) (2023)
- [Seeing Text in the Dark: Algorithm and Benchmark](https://mlsanity.com/paper/2404.08965/) (2024)
- [Extremely Low-light Image Enhancement with Scene Text Restoration](https://mlsanity.com/paper/2204.00630/) (2022)
- [Self-Reference Deep Adaptive Curve Estimation for Low-Light Image Enhancement](https://mlsanity.com/paper/2308.08197/) (2023)
- [Text in the Dark: Extremely Low-Light Text Image Enhancement](https://mlsanity.com/paper/2404.14135/) (2024)

## Abstract (arXiv)

Accurate text recognition in low-light environments is essential for intelligent systems in applications ranging from autonomous vehicles to smart surveillance. However, challenges such as poor illumination and noise interference remain underexplored. To address this gap, we introduce LSTR, a large-scale Low-light Scene Text Recognition dataset comprising 11,273 low-light images generated from well-lit datasets (ICDAR2015, IIIT5K, and WordArt), along with ESTR, which includes 60 real nighttime street-scene images in English and Spanish for exclusive evaluation. We explore two solution strategies: (1) employing Optical Character Recognition (OCR) models with fine-tuning and LoRA-based fine-tuning and (2) a joint training strategy that integrates a low-light image enhancement (LLIE) module with an OCR model. In particular, we propose a novel re-render LLIE (RLLIE) module, which demonstrates improved performance on real-world data. Through extensive experimentation, we analyze various training strategies and address a key research question: How bright is bright enough for effective scene text recognition? Our results indicate that standalone LLIE or OCR models perform inadequately under low-light conditions, highlighting the advantages of specialized, jointly trained text-centric approaches. Additionally, we provide a comprehensive benchmark to support future research in robust low-light scene text recognition. https://huggingface.co/datasets/lumimusta/Low-lightSceneTextDataset.