# Seeing Text in the Dark: Algorithm and Benchmark

arXiv: https://arxiv.org/abs/2404.08965 · HTML: https://mlsanity.com/paper/2404.08965/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 45 references that are in the map.
- First posted on arXiv 13 Apr 2024.

## Builds on (most cited first, 27 of 27)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [Zero-Reference Deep Curve Estimation for Low-Light Image Enhancement](https://mlsanity.com/paper/2001.06826/) (2020)
- [Synthetic Data for Text Localisation in Natural Images](https://mlsanity.com/paper/1604.06646/) (2016)
- [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)
- [Real-time Scene Text Detection with Differentiable Binarization](https://mlsanity.com/paper/1911.08947/) (2019)
- [ABCNet: Real-time Scene Text Spotting with Adaptive Bezier-Curve Network](https://mlsanity.com/paper/2002.10200/) (2020)
- [Total-Text: A Comprehensive Dataset for Scene Text Detection and Recognition](https://mlsanity.com/paper/1710.10400/) (2017)
- [Shape Robust Text Detection with Progressive Scale Expansion Network](https://mlsanity.com/paper/1903.12473/) (2019)
- [TextSnake: A Flexible Representation for Detecting Text of Arbitrary Shapes](https://mlsanity.com/paper/1807.01544/) (2018)
- [Efficient and Accurate Arbitrary-Shaped Text Detection with Pixel Aggregation Network](https://mlsanity.com/paper/1908.05900/) (2019)
- [Real-Time Scene Text Detection with Differentiable Binarization and Adaptive Scale Fusion](https://mlsanity.com/paper/2202.10304/) (2022)
- [Dynamic Snake Convolution based on Topological Geometric Constraints for Tubular Structure Segmentation](https://mlsanity.com/paper/2307.08388/) (2023)
- [Detecting Oriented Text in Natural Images by Linking Segments](https://mlsanity.com/paper/1703.06520/) (2017)
- [Fourier Contour Embedding for Arbitrary-Shaped Text Detection](https://mlsanity.com/paper/2104.10442/) (2021)
- [Deep Relational Reasoning Graph Network for Arbitrary Shape Text Detection](https://mlsanity.com/paper/2003.07493/) (2020)
- [ContourNet: Taking a Further Step toward Accurate Arbitrary-shaped Scene Text Detection](https://mlsanity.com/paper/2004.04940/) (2020)
- [Few Could Be Better Than All: Feature Sampling and Grouping for Scene Text Detection](https://mlsanity.com/paper/2203.15221/) (2022)
- [DPText-DETR: Towards Better Scene Text Detection with Dynamic Points in Transformer](https://mlsanity.com/paper/2207.04491/) (2022)
- [Adaptive Boundary Proposal Network for Arbitrary Shape Text Detection](https://mlsanity.com/paper/2107.12664/) (2021)
- [TextRay: Contour-based Geometric Modeling for Arbitrary-shaped Scene Text Detection](https://mlsanity.com/paper/2008.04851/) (2020)
- [Arbitrary Shape Text Detection via Boundary Transformer](https://mlsanity.com/paper/2205.05320/) (2022)
- [ReLaText: Exploiting Visual Relationships for Arbitrary-Shaped Scene Text Detection with Graph Convolutional Networks](https://mlsanity.com/paper/2003.06999/) (2020)
- [Towards Robust Real-Time Scene Text Detection: From Semantic to Instance Representation Learning](https://mlsanity.com/paper/2308.07202/) (2023)
- [Extremely Low-light Image Enhancement with Scene Text Restoration](https://mlsanity.com/paper/2204.00630/) (2022)
- [PuzzleNet: Scene Text Detection by Segment Context Graph Learning](https://mlsanity.com/paper/2002.11371/) (2020)

## Built on by (most cited first, 8 of 8)

- [SFFNet: A Wavelet-Based Spatial and Frequency Domain Fusion Network for Remote Sensing Segmentation](https://mlsanity.com/paper/2405.01992/) (2024)
- [FDCE-Net: Underwater Image Enhancement with Embedding Frequency and Dual Color Encoder](https://mlsanity.com/paper/2404.17936/) (2024)
- [Spatial-frequency Dual-Domain Feature Fusion Network for Low-Light Remote Sensing Image Enhancement](https://mlsanity.com/paper/2404.17400/) (2024)
- [Millimeter Wave Radar-based Human Activity Recognition for Healthcare Monitoring Robot](https://mlsanity.com/paper/2405.01882/) (2024)
- [KAN See In the Dark](https://mlsanity.com/paper/2409.03404/) (2024)
- [Underwater Variable Zoom: Depth-Guided Perception Network for Underwater Image Enhancement](https://mlsanity.com/paper/2404.17883/) (2024)
- [MorphText: Deep Morphology Regularized Arbitrary-shape Scene Text Detection](https://mlsanity.com/paper/2404.17151/) (2024)
- [Reading in the Dark: Low-light Scene Text Recognition](https://mlsanity.com/paper/2604.23685/) (2026)

## Abstract (arXiv)

Localizing text in low-light environments is challenging due to visual degradations. Although a straightforward solution involves a two-stage pipeline with low-light image enhancement (LLE) as the initial step followed by detector, LLE is primarily designed for human vision instead of machine and can accumulate errors. In this work, we propose an efficient and effective single-stage approach for localizing text in dark that circumvents the need for LLE. We introduce a constrained learning module as an auxiliary mechanism during the training stage of the text detector. This module is designed to guide the text detector in preserving textual spatial features amidst feature map resizing, thus minimizing the loss of spatial information in texts under low-light visual degradations. Specifically, we incorporate spatial reconstruction and spatial semantic constraints within this module to ensure the text detector acquires essential positional and contextual range knowledge. Our approach enhances the original text detector's ability to identify text's local topological features using a dynamic snake feature pyramid network and adopts a bottom-up contour shaping strategy with a novel rectangular accumulation technique for accurate delineation of streamlined text features. In addition, we present a comprehensive low-light dataset for arbitrary-shaped text, encompassing diverse scenes and languages. Notably, our method achieves state-of-the-art results on this low-light dataset and exhibits comparable performance on standard normal light datasets. The code and dataset will be released.