# Progressive Evolution from Single-Point to Polygon for Scene Text

arXiv: https://arxiv.org/abs/2312.13778 · HTML: https://mlsanity.com/paper/2312.13778/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 42 references that are in the map.
- First posted on arXiv 21 Dec 2023.

## Builds on (most cited first, 30 of 31)

- [SSD: Single Shot MultiBox Detector](https://mlsanity.com/paper/1512.02325/) (2015)
- [Synthetic Data for Text Localisation in Natural Images](https://mlsanity.com/paper/1604.06646/) (2016)
- [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)
- [Synthetic Data and Artificial Neural Networks for Natural Scene Text Recognition](https://mlsanity.com/paper/1406.2227/) (2014)
- [Real-time Scene Text Detection with Differentiable Binarization](https://mlsanity.com/paper/1911.08947/) (2019)
- [Mask TextSpotter: An End-to-End Trainable Neural Network for Spotting Text with Arbitrary Shapes](https://mlsanity.com/paper/1908.08207/) (2019)
- [ABCNet: Real-time Scene Text Spotting with Adaptive Bezier-Curve Network](https://mlsanity.com/paper/2002.10200/) (2020)
- [Shape Robust Text Detection with Progressive Scale Expansion Network](https://mlsanity.com/paper/1903.12473/) (2019)
- [TextBoxes: A Fast Text Detector with a Single Deep Neural Network](https://mlsanity.com/paper/1611.06779/) (2016)
- [Efficient and Accurate Arbitrary-Shaped Text Detection with Pixel Aggregation Network](https://mlsanity.com/paper/1908.05900/) (2019)
- [SVTR: Scene Text Recognition with a Single Visual Model](https://mlsanity.com/paper/2205.00159/) (2022)
- [Detecting Text in Natural Image with Connectionist Text Proposal Network](https://mlsanity.com/paper/1609.03605/) (2016)
- [Editing Text in the Wild](https://mlsanity.com/paper/1908.03047/) (2019)
- [DeepSolo: Let Transformer Decoder with Explicit Points Solo for Text Spotting](https://mlsanity.com/paper/2211.10772/) (2022)
- [SwinTextSpotter: Scene Text Spotting via Better Synergy between Text Detection and Text Recognition](https://mlsanity.com/paper/2203.10209/) (2022)
- [Text Spotting Transformers](https://mlsanity.com/paper/2204.01918/) (2022)
- [SPTS v2: Single-Point Scene Text Spotting](https://mlsanity.com/paper/2301.01635/) (2023)
- [SPTS: Single-Point Text Spotting](https://mlsanity.com/paper/2112.07917/) (2021)
- [Towards Weakly-Supervised Text Spotting using a Multi-Task Transformer](https://mlsanity.com/paper/2202.05508/) (2022)
- [MMOCR: A Comprehensive Toolbox for Text Detection, Recognition and Understanding](https://mlsanity.com/paper/2108.06543/) (2021)
- [Deep Direct Regression for Multi-Oriented Scene Text Detection](https://mlsanity.com/paper/1703.08289/) (2017)
- [Exploring Stroke-Level Modifications for Scene Text Editing](https://mlsanity.com/paper/2212.01982/) (2022)
- [CDistNet: Perceiving Multi-Domain Character Distance for Robust Text Recognition](https://mlsanity.com/paper/2111.11011/) (2021)
- [ESTextSpotter: Towards Better Scene Text Spotting with Explicit Synergy in Transformer](https://mlsanity.com/paper/2308.10147/) (2023)
- [Towards Unified Scene Text Spotting based on Sequence Generation](https://mlsanity.com/paper/2304.03435/) (2023)
- [WordSup: Exploiting Word Annotations for Character based Text Detection](https://mlsanity.com/paper/1708.06720/) (2017)
- [WeText: Scene Text Detection under Weak Supervision](https://mlsanity.com/paper/1710.04826/) (2017)
- [PERT: A Progressively Region-based Network for Scene Text Removal](https://mlsanity.com/paper/2106.13029/) (2021)
- [PBFormer: Capturing Complex Scene Text Shape with Polynomial Band Transformer](https://mlsanity.com/paper/2308.15004/) (2023)

## Built on by (most cited first, 1 of 1)

- [Edge Approximation Text Detector](https://mlsanity.com/paper/2504.04001/) (2025)

## Abstract (arXiv)

The advancement of text shape representations towards compactness has enhanced text detection and spotting performance, but at a high annotation cost. Current models use single-point annotations to reduce costs, yet they lack sufficient localization information for downstream applications. To overcome this limitation, we introduce Point2Polygon, which can efficiently transform single-points into compact polygons. Our method uses a coarse-to-fine process, starting with creating and selecting anchor points based on recognition confidence, then vertically and horizontally refining the polygon using recognition information to optimize its shape. We demonstrate the accuracy of the generated polygons through extensive experiments: 1) By creating polygons from ground truth points, we achieved an accuracy of 82.0% on ICDAR 2015; 2) In training detectors with polygons generated by our method, we attained 86% of the accuracy relative to training with ground truth (GT); 3) Additionally, the proposed Point2Polygon can be seamlessly integrated to empower single-point spotters to generate polygons. This integration led to an impressive 82.5% accuracy for the generated polygons. It is worth mentioning that our method relies solely on synthetic recognition information, eliminating the need for any manual annotation beyond single points.