# ReLaText: Exploiting Visual Relationships for Arbitrary-Shaped Scene Text Detection with Graph Convolutional Networks

arXiv: https://arxiv.org/abs/2003.06999 · HTML: https://mlsanity.com/paper/2003.06999/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Mar 2020.

## Built on by (most cited first, 20 of 20)

- [Fourier Contour Embedding for Arbitrary-Shaped Text Detection](https://mlsanity.com/paper/2104.10442/) (2021)
- [Robust Table Detection and Structure Recognition from Heterogeneous Document Images](https://mlsanity.com/paper/2203.09056/) (2022)
- [TPSNet: Reverse Thinking of Thin Plate Splines for Arbitrary Shape Scene Text Representation](https://mlsanity.com/paper/2110.12826/) (2021)
- [Mask is All You Need: Rethinking Mask R-CNN for Dense and Arbitrary-Shaped Scene Text Detection](https://mlsanity.com/paper/2109.03426/) (2021)
- [TextDCT: Arbitrary-Shaped Text Detection via Discrete Cosine Transform Mask](https://mlsanity.com/paper/2206.13381/) (2022)
- [Towards Robust Real-Time Scene Text Detection: From Semantic to Instance Representation Learning](https://mlsanity.com/paper/2308.07202/) (2023)
- [Text Growing on Leaf](https://mlsanity.com/paper/2209.03016/) (2022)
- [FAST: Faster Arbitrarily-Shaped Text Detector with Minimalist Kernel Representation](https://mlsanity.com/paper/2111.02394/) (2021)
- [Seeing Text in the Dark: Algorithm and Benchmark](https://mlsanity.com/paper/2404.08965/) (2024)
- [Unified Line and Paragraph Detection by Graph Convolutional Networks](https://mlsanity.com/paper/2203.09638/) (2022)
- [Zoom Text Detector](https://mlsanity.com/paper/2209.03014/) (2022)
- [DeepSolo++: Let Transformer Decoder with Explicit Points Solo for Multilingual Text Spotting](https://mlsanity.com/paper/2305.19957/) (2023)
- [Spotlight Text Detector: Spotlight on Candidate Regions Like a Camera](https://mlsanity.com/paper/2409.16820/) (2024)
- [PBFormer: Capturing Complex Scene Text Shape with Polynomial Band Transformer](https://mlsanity.com/paper/2308.15004/) (2023)
- [CT-Net: Arbitrary-Shaped Text Detection via Contour Transformer](https://mlsanity.com/paper/2307.13310/) (2023)
- [StrokeNet: Stroke Assisted and Hierarchical Graph Reasoning Networks](https://mlsanity.com/paper/2111.11718/) (2021)
- [Dynamic Relation Transformer for Contextual Text Block Detection](https://mlsanity.com/paper/2401.09232/) (2024)
- [OG-HFYOLO :Orientation gradient guidance and heterogeneous feature fusion for deformation table cell instance segmentation](https://mlsanity.com/paper/2504.20682/) (2025)
- [Adaptive Shrink-Mask for Text Detection](https://mlsanity.com/paper/2111.09560/) (2021)
- [MorphText: Deep Morphology Regularized Arbitrary-shape Scene Text Detection](https://mlsanity.com/paper/2404.17151/) (2024)

## Abstract (arXiv)

We introduce a new arbitrary-shaped text detection approach named ReLaText by formulating text detection as a visual relationship detection problem. To demonstrate the effectiveness of this new formulation, we start from using a "link" relationship to address the challenging text-line grouping problem firstly. The key idea is to decompose text detection into two subproblems, namely detection of text primitives and prediction of link relationships between nearby text primitive pairs. Specifically, an anchor-free region proposal network based text detector is first used to detect text primitives of different scales from different feature maps of a feature pyramid network, from which a text primitive graph is constructed by linking each pair of nearby text primitives detected from a same feature map with an edge. Then, a Graph Convolutional Network (GCN) based link relationship prediction module is used to prune wrongly-linked edges in the text primitive graph to generate a number of disjoint subgraphs, each representing a detected text instance. As GCN can effectively leverage context information to improve link prediction accuracy, our GCN based text-line grouping approach can achieve better text detection accuracy than previous text-line grouping methods, especially when dealing with text instances with large inter-character or very small inter-line spacings. Consequently, the proposed ReLaText achieves state-of-the-art performance on five public text detection benchmarks, namely RCTW-17, MSRA-TD500, Total-Text, CTW1500 and DAST1500.