# Detecting Curve Text in the Wild: New Dataset and New Solution

arXiv: https://arxiv.org/abs/1712.02170 · HTML: https://mlsanity.com/paper/1712.02170/

## Key facts

- Cited by 83 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Dec 2017.

## Built on by (most cited first, 30 of 83)

- [OCRBench v2: An Improved Benchmark for Evaluating Large Multimodal Models on Visual Text Localization and Reasoning](https://mlsanity.com/paper/2501.00321/) (2024)
- [TextOCR: Towards large-scale end-to-end reasoning for arbitrary-shaped scene text](https://mlsanity.com/paper/2105.05486/) (2021)
- [The All-Seeing Project: Towards Panoptic Visual Recognition and Understanding of the Open World](https://mlsanity.com/paper/2308.01907/) (2023)
- [Draw-and-Understand: Leveraging Visual Prompts to Enable MLLMs to Comprehend What You Want](https://mlsanity.com/paper/2403.20271/) (2024)
- [Towards End-to-End Unified Scene Text Detection and Layout Analysis](https://mlsanity.com/paper/2203.15143/) (2022)
- [CC-OCR: A Comprehensive and Challenging OCR Benchmark for Evaluating Large Multimodal Models in Literacy](https://mlsanity.com/paper/2412.02210/) (2024)
- [PAN++: Towards Efficient and Accurate End-to-End Spotting of Arbitrarily-Shaped Text](https://mlsanity.com/paper/2105.00405/) (2021)
- [Few Could Be Better Than All: Feature Sampling and Grouping for Scene Text Detection](https://mlsanity.com/paper/2203.15221/) (2022)
- [Transformers in Remote Sensing: A Survey](https://mlsanity.com/paper/2209.01206/) (2022)
- [Open Images V5 Text Annotation and Yet Another Mask Text Spotter](https://mlsanity.com/paper/2106.12326/) (2021)
- [Language Matters: A Weakly Supervised Vision-Language Pre-training Approach for Scene Text Detection and Spotting](https://mlsanity.com/paper/2203.03911/) (2022)
- [Advancing Sequential Numerical Prediction in Autoregressive Models](https://mlsanity.com/paper/2505.13077/) (2025)
- [Visual Text Generation in the Wild](https://mlsanity.com/paper/2407.14138/) (2024)
- [A Multiplexed Network for End-to-End, Multilingual OCR](https://mlsanity.com/paper/2103.15992/) (2021)
- [Vision-Language Pre-Training for Boosting Scene Text Detectors](https://mlsanity.com/paper/2204.13867/) (2022)
- [Kernel Proposal Network for Arbitrary Shape Text Detection](https://mlsanity.com/paper/2203.06410/) (2022)
- [Arbitrary Shape Text Detection via Segmentation with Probability Maps](https://mlsanity.com/paper/2208.12419/) (2022)
- [I3CL:Intra- and Inter-Instance Collaborative Learning for Arbitrary-shaped Scene Text Detection](https://mlsanity.com/paper/2108.01343/) (2021)
- [Exploring the Capabilities of Large Multimodal Models on Dense Text](https://mlsanity.com/paper/2405.06706/) (2024)
- [A Token-level Text Image Foundation Model for Document Understanding](https://mlsanity.com/paper/2503.02304/) (2025)
- [CentripetalText: An Efficient Text Instance Representation for Scene Text Detection](https://mlsanity.com/paper/2107.05945/) (2021)
- [When Semantics Mislead Vision: Mitigating Large Multimodal Models Hallucinations in Scene Text Spotting and Understanding](https://mlsanity.com/paper/2506.05551/) (2025)
- [Text Growing on Leaf](https://mlsanity.com/paper/2209.03016/) (2022)
- [Boosting Low-Data Instance Segmentation by Unsupervised Pre-training with Saliency Prompt](https://mlsanity.com/paper/2302.01171/) (2023)
- [StrucTexTv3: An Efficient Vision-Language Model for Text-rich Image Perception, Comprehension, and Beyond](https://mlsanity.com/paper/2405.21013/) (2024)
- [Out of Length Text Recognition with Sub-String Matching](https://mlsanity.com/paper/2407.12317/) (2024)
- [Arbitrary Reading Order Scene Text Spotter with Local Semantics Guidance](https://mlsanity.com/paper/2412.10159/) (2024)
- [FAST: Faster Arbitrarily-Shaped Text Detector with Minimalist Kernel Representation](https://mlsanity.com/paper/2111.02394/) (2021)
- [Multimodal Large Language Models for Text-rich Image Understanding: A Comprehensive Review](https://mlsanity.com/paper/2502.16586/) (2025)
- [Hierarchical Text Spotter for Joint Text Spotting and Layout Analysis](https://mlsanity.com/paper/2310.17674/) (2023)

## Abstract (arXiv)

Scene text detection has been made great progress in recent years. The detection manners are evolving from axis-aligned rectangle to rotated rectangle and further to quadrangle. However, current datasets contain very little curve text, which can be widely observed in scene images such as signboard, product name and so on. To raise the concerns of reading curve text in the wild, in this paper, we construct a curve text dataset named CTW1500, which includes over 10k text annotations in 1,500 images (1000 for training and 500 for testing). Based on this dataset, we pioneering propose a polygon based curve text detector (CTD) which can directly detect curve text without empirical combination. Moreover, by seamlessly integrating the recurrent transverse and longitudinal offset connection (TLOC), the proposed method can be end-to-end trainable to learn the inherent connection among the position offsets. This allows the CTD to explore context information instead of predicting points independently, resulting in more smooth and accurate detection. We also propose two simple but effective post-processing methods named non-polygon suppress (NPS) and polygonal non-maximum suppression (PNMS) to further improve the detection accuracy. Furthermore, the proposed approach in this paper is designed in an universal manner, which can also be trained with rectangular or quadrilateral bounding boxes without extra efforts. Experimental results on CTW-1500 demonstrate our method with only a light backbone can outperform state-of-the-art methods with a large margin. By evaluating only in the curve or non-curve subset, the CTD + TLOC can still achieve the best results. Code is available at https://github.com/Yuliang-Liu/Curve-Text-Detector.