Papers › PGNet: Real-time Arbitrarily-Shaped Text Spotting with Point Gathering Network

PGNet: Real-time Arbitrarily-Shaped Text Spotting with Point Gathering Network

12 Apr 2021arXiv:2104.05458archive 2025-07-28

Pengfei Wang, Chengquan Zhang, Fei Qi, Shanshan Liu, Xiaoqiang Zhang, Pengyuan Lyu, Junyu Han, Jingtuo Liu, Errui Ding, Guangming Shi

The reading of arbitrarily-shaped text has received increasing research attention. However, existing text spotters are mostly built on two-stage frameworks or character-based methods, which suffer from either Non-Maximum Suppression (NMS), Region-of-Interest (RoI) operations, or character-level annotations. In this paper, to address the above problems, we propose a novel fully convolutional Point Gathering Network (PGNet) for reading arbitrarily-shaped text in real-time. The PGNet is a single-shot text spotter, where the pixel-level character classification map is learned with proposed PG-CTC loss avoiding the usage of character-level annotations. With a PG-CTC decoder, we gather high-level character classification vectors from two-dimensional space and decode them into text symbols without NMS and RoI operations involved, which guarantees high efficiency. Additionally, reasoning the relations between each character and its neighbors, a graph refinement module (GRM) is proposed to optimize the coarse recognition and improve the end-to-end performance. Experiments prove that the proposed method achieves competitive accuracy, meanwhile significantly improving the running speed. In particular, in Total-Text, it runs at 46.7 FPS, surpassing the previous spotters with a large margin.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

PaddlePaddle/PaddleOCR officialpaddleApache-2.0 report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

DecoderOptical Character Recognition (OCR)Scene Text DetectionText Spotting

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Scene Text Detection ICDAR 2015 MCLAB_FCN F-Measure 53.6 #41 of 43 Archive leaderboard report
Scene Text Detection ICDAR 2015 MCLAB_FCN Precision 70.8 #41 of 43 Archive leaderboard report
Scene Text Detection ICDAR 2015 MCLAB_FCN Recall 43.0 #41 of 43 Archive leaderboard report
Scene Text Detection ICDAR 2015 PGNet-A Accuracy 62.3 #42 of 43 Archive leaderboard report
Text Spotting ICDAR 2015 PGNet F-measure (%) - Generic Lexicon 63.5 #11 of 18 Archive leaderboard report
Text Spotting ICDAR 2015 PGNet F-measure (%) - Strong Lexicon 83.3 #11 of 18 Archive leaderboard report
Text Spotting ICDAR 2015 PGNet F-measure (%) - Weak Lexicon 78.3 #11 of 18 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Introduced by this paper: PGNet

PGNet

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections