Reading in the Dark: Low-light Scene Text Recognition

• URL: http://arxiv.org/abs/2604.23685v1
• Date: Sun, 26 Apr 2026 12:57:48 GMT
• Title: Reading in the Dark: Low-light Scene Text Recognition
• Abstract summary: We introduce LSTR, a large-scale Low-light Scene Text Recognition dataset.<n>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.<n>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.
• Score: 19.782261736974473
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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: \emph{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-light_Scene_Text_Dataset.

Related papers

• EPRBench: A High-Quality Benchmark Dataset for Event Stream Based Visual Place Recognition [54.55914886780534]
  Event stream-based Visual Place Recognition (VPR) is an emerging research direction that offers a compelling solution to the instability of conventional visible-light cameras under challenging conditions such as low illumination, overexposure, and high-speed motion.<n>We introduce EPRBench, a high-quality benchmark specifically designed for event stream-based VPR.<n>EPRBench comprises 10K event sequences and 65K event frames, collected using both handheld and vehicle-mounted setups to comprehensively capture real-world challenges across diverse viewpoints, weather conditions, and lighting scenarios.
  arXiv  Detail & Related papers  (2026-02-13T13:25:05Z)
• Scene Text Detection and Recognition "in light of" Challenging Environmental Conditions using Aria Glasses Egocentric Vision Cameras [0.7366405857677226]
  Scene Text Detection and Recognition (STDR) becomes a straightforward choice through the lens of egocentric vision.<n>This paper investigates how environmental variables, such as lighting, distance, and resolution, affect the performance of STDR algorithms in real-world scenarios.
  arXiv  Detail & Related papers  (2025-07-22T08:12:00Z)
• Towards Visual Text Grounding of Multimodal Large Language Model [74.22413337117617]
  We introduce TRIG, a novel task with a newly designed instruction dataset for benchmarking text-rich image grounding.<n>Specifically, we propose an OCR-LLM-human interaction pipeline to create 800 manually annotated question-answer pairs as a benchmark.<n>A comprehensive evaluation of various MLLMs on our proposed benchmark exposes substantial limitations in their grounding capability on text-rich images.
  arXiv  Detail & Related papers  (2025-04-07T12:01:59Z)
• BVI-RLV: A Fully Registered Dataset and Benchmarks for Low-Light Video Enhancement [56.97766265018334]
  This paper introduces a low-light video dataset, consisting of 40 scenes with various motion scenarios under two distinct low-lighting conditions. We provide fully registered ground truth data captured in normal light using a programmable motorized dolly and refine it via an image-based approach for pixel-wise frame alignment across different light levels. Our experimental results demonstrate the significance of fully registered video pairs for low-light video enhancement (LLVE) and the comprehensive evaluation shows that the models trained with our dataset outperform those trained with the existing datasets.
  arXiv  Detail & Related papers  (2024-07-03T22:41:49Z)
• Text in the Dark: Extremely Low-Light Text Image Enhancement [20.631833980353704]
  Low-light text images are common in natural scenes, making scene text detection and recognition challenging. We propose a novel encoder-decoder framework with an edge-aware attention module to focus on scene text regions during enhancement. Our proposed method uses novel text detection and edge reconstruction losses to emphasize low-level scene text features, leading to successful text extraction.
  arXiv  Detail & Related papers  (2024-04-22T12:39:12Z)
• Seeing Text in the Dark: Algorithm and Benchmark [28.865779563872977]
  In this work, we propose an efficient and effective single-stage approach for localizing text in dark. We introduce a constrained learning module as an auxiliary mechanism during the training stage of the text detector. We present a comprehensive low-light dataset for arbitrary-shaped text, encompassing diverse scenes and languages.
  arXiv  Detail & Related papers  (2024-04-13T11:07:10Z)
• Towards Robust Event-guided Low-Light Image Enhancement: A Large-Scale Real-World Event-Image Dataset and Novel Approach [7.974102031202597]
  We propose a real-world (indoor and outdoor) dataset comprising over 30K pairs of images and events under both low and normal illumination conditions. Based on the dataset, we propose a novel event-guided LIE approach, called EvLight, towards robust performance in real-world low-light scenes.
  arXiv  Detail & Related papers  (2024-04-01T00:18:17Z)
• BVI-Lowlight: Fully Registered Benchmark Dataset for Low-Light Video Enhancement [44.1973928137492]
  This paper introduces a novel low-light video dataset, consisting of 40 scenes in various motion scenarios under two low-lighting conditions. We provide fully registered ground truth data captured in normal light using a programmable motorized dolly. We refine them via image-based post-processing to ensure the pixel-wise alignment of frames in different light levels.
  arXiv  Detail & Related papers  (2024-02-03T00:40:22Z)
• Toward Fast, Flexible, and Robust Low-Light Image Enhancement [87.27326390675155]
  We develop a new Self-Calibrated Illumination (SCI) learning framework for fast, flexible, and robust brightening images in real-world low-light scenarios. Considering the computational burden of the cascaded pattern, we construct the self-calibrated module which realizes the convergence between results of each stage. We make comprehensive explorations to SCI's inherent properties including operation-insensitive adaptability and model-irrelevant generality.
  arXiv  Detail & Related papers  (2022-04-21T14:40:32Z)
• Learning Deep Context-Sensitive Decomposition for Low-Light Image Enhancement [58.72667941107544]
  A typical framework is to simultaneously estimate the illumination and reflectance, but they disregard the scene-level contextual information encapsulated in feature spaces. We develop a new context-sensitive decomposition network architecture to exploit the scene-level contextual dependencies on spatial scales. We develop a lightweight CSDNet (named LiteCSDNet) by reducing the number of channels.
  arXiv  Detail & Related papers  (2021-12-09T06:25:30Z)
• Low Light Image Enhancement via Global and Local Context Modeling [164.85287246243956]
  We introduce a context-aware deep network for low-light image enhancement. First, it features a global context module that models spatial correlations to find complementary cues over full spatial domain. Second, it introduces a dense residual block that captures local context with a relatively large receptive field.
  arXiv  Detail & Related papers  (2021-01-04T09:40:54Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.