# Deep Direct Regression for Multi-Oriented Scene Text Detection

arXiv: https://arxiv.org/abs/1703.08289 · HTML: https://mlsanity.com/paper/1703.08289/

## Key facts

- Cited by 37 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Mar 2017.

## Built on by (most cited first, 30 of 37)

- [Real-Time Scene Text Detection with Differentiable Binarization and Adaptive Scale Fusion](https://mlsanity.com/paper/2202.10304/) (2022)
- [ABCNet v2: Adaptive Bezier-Curve Network for Real-time End-to-end Text Spotting](https://mlsanity.com/paper/2105.03620/) (2021)
- [PAN++: Towards Efficient and Accurate End-to-End Spotting of Arbitrarily-Shaped Text](https://mlsanity.com/paper/2105.00405/) (2021)
- [Adaptive Boundary Proposal Network for Arbitrary Shape Text Detection](https://mlsanity.com/paper/2107.12664/) (2021)
- [Turning a CLIP Model into a Scene Text Detector](https://mlsanity.com/paper/2302.14338/) (2023)
- [Arbitrary Shape Text Detection via Boundary Transformer](https://mlsanity.com/paper/2205.05320/) (2022)
- [PolarMask++: Enhanced Polar Representation for Single-Shot Instance Segmentation and Beyond](https://mlsanity.com/paper/2105.02184/) (2021)
- [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)
- [Kernel Proposal Network for Arbitrary Shape Text Detection](https://mlsanity.com/paper/2203.06410/) (2022)
- [RSDet++: Point-based Modulated Loss for More Accurate Rotated Object Detection](https://mlsanity.com/paper/2109.11906/) (2021)
- [Arbitrary Shape Text Detection via Segmentation with Probability Maps](https://mlsanity.com/paper/2208.12419/) (2022)
- [Towards Robust Real-Time Scene Text Detection: From Semantic to Instance Representation Learning](https://mlsanity.com/paper/2308.07202/) (2023)
- [Video Text Tracking With a Spatio-Temporal Complementary Model](https://mlsanity.com/paper/2111.04987/) (2021)
- [Turning a CLIP Model into a Scene Text Spotter](https://mlsanity.com/paper/2308.10408/) (2023)
- [Graph Fusion Network for Multi-Oriented Object Detection](https://mlsanity.com/paper/2205.03562/) (2022)
- [Get More for Less in Decentralized Learning Systems](https://mlsanity.com/paper/2306.04377/) (2023)
- [Detection and Rectification of Arbitrary Shaped Scene Texts by using Text Keypoints and Links](https://mlsanity.com/paper/2103.00785/) (2021)
- [A Systematic IoU-Related Method: Beyond Simplified Regression for Better Localization](https://mlsanity.com/paper/2112.01793/) (2021)
- [EAFormer: Scene Text Segmentation with Edge-Aware Transformers](https://mlsanity.com/paper/2407.17020/) (2024)
- [A Survey on Deep Domain Adaptation and Tiny Object Detection Challenges, Techniques and Datasets](https://mlsanity.com/paper/2107.07927/) (2021)
- [Active-SAOOD: Active Sparsely Annotated Oriented Object Detection in Remote Sensing Images](https://mlsanity.com/paper/2605.10162/) (2026)
- [Conceptual Text Region Network: Cognition-Inspired Accurate Scene Text Detection](https://mlsanity.com/paper/2103.09179/) (2021)
- [DUET: Detection Utilizing Enhancement for Text in Scanned or Captured Documents](https://mlsanity.com/paper/2106.05542/) (2021)
- [Progressive Evolution from Single-Point to Polygon for Scene Text](https://mlsanity.com/paper/2312.13778/) (2023)
- [Artistic-style text detector and a new Movie-Poster dataset](https://mlsanity.com/paper/2406.16307/) (2024)
- [A DCNN-based Arbitrarily-Oriented Object Detector for Quality Control and Inspection Application](https://mlsanity.com/paper/2101.07383/) (2021)
- [Arbitrary-Shaped Text Detection withAdaptive Text Region Representation](https://mlsanity.com/paper/2104.00297/) (2021)
- [Bidirectional Regression for Arbitrary-Shaped Text Detection](https://mlsanity.com/paper/2107.06129/) (2021)
- [DPTNet: A Dual-Path Transformer Architecture for Scene Text Detection](https://mlsanity.com/paper/2208.09878/) (2022)

## Abstract (arXiv)

In this paper, we first provide a new perspective to divide existing high performance object detection methods into direct and indirect regressions. Direct regression performs boundary regression by predicting the offsets from a given point, while indirect regression predicts the offsets from some bounding box proposals. Then we analyze the drawbacks of the indirect regression, which the recent state-of-the-art detection structures like Faster-RCNN and SSD follows, for multi-oriented scene text detection, and point out the potential superiority of direct regression. To verify this point of view, we propose a deep direct regression based method for multi-oriented scene text detection. Our detection framework is simple and effective with a fully convolutional network and one-step post processing. The fully convolutional network is optimized in an end-to-end way and has bi-task outputs where one is pixel-wise classification between text and non-text, and the other is direct regression to determine the vertex coordinates of quadrilateral text boundaries. The proposed method is particularly beneficial for localizing incidental scene texts. On the ICDAR2015 Incidental Scene Text benchmark, our method achieves the F1-measure of 81%, which is a new state-of-the-art and significantly outperforms previous approaches. On other standard datasets with focused scene texts, our method also reaches the state-of-the-art performance.