{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/pgnet-real-time-arbitrarily-shaped-text","title":"PGNet: Real-time Arbitrarily-Shaped Text Spotting with Point Gathering Network","arxiv_id":"2104.05458","date":"2021-04-12","proceeding":null,"authors":["Pengfei Wang","Chengquan Zhang","Fei Qi","Shanshan Liu","Xiaoqiang Zhang","Pengyuan Lyu","Junyu Han","Jingtuo Liu","Errui Ding","Guangming Shi"],"abstract":"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.","url_abs":"https://arxiv.org/abs/2104.05458v1","url_pdf":"https://arxiv.org/pdf/2104.05458v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"pgnet-real-time-arbitrarily-shaped-text","repo_url":"https://github.com/PaddlePaddle/PaddleOCR","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"paddle","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"pgnet-real-time-arbitrarily-shaped-text","repo_url":"https://github.com/2024-MindSpore-1/Code3/tree/main/PGNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"optical-character-recognition","task_name":"Optical Character Recognition (OCR)"},{"task_slug":"scene-text-detection","task_name":"Scene Text Detection"},{"task_slug":"text-spotting","task_name":"Text Spotting"}],"methods":[{"method_slug":"pgnet","method_name":"PGNet"}],"datasets_introduced":[],"methods_introduced":[{"slug":"pgnet","name":"PGNet","full_name":"Point Gathering Network"}],"results":[{"leaderboard":"/sota/scene-text-detection-on-icdar-2015","task":"Scene Text Detection","dataset":"ICDAR 2015","model":"MCLAB_FCN","rank_in_archive_order":41,"of":43,"metrics":{"F-Measure":"53.6","Precision":"70.8","Recall":"43.0"},"uses_additional_data":false},{"leaderboard":"/sota/scene-text-detection-on-icdar-2015","task":"Scene Text Detection","dataset":"ICDAR 2015","model":"PGNet-A","rank_in_archive_order":42,"of":43,"metrics":{"Accuracy":"62.3"},"uses_additional_data":false},{"leaderboard":"/sota/text-spotting-on-icdar-2015","task":"Text Spotting","dataset":"ICDAR 2015","model":"PGNet","rank_in_archive_order":11,"of":18,"metrics":{"F-measure (%) - Generic Lexicon":"63.5","F-measure (%) - Strong Lexicon":"83.3","F-measure (%) - Weak Lexicon":"78.3"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2104.05458","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}