{"url":"/method/pgnet","slug":"pgnet","name":"PGNet","full_name":"Point Gathering Network","full_name_withheld":false,"description_markdown":"**PGNet** is a point-gathering network for reading arbitrarily-shaped text in real-time. It 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.","description_state":"present","introduced_year":null,"introduced_by":{"title":"PGNet: Real-time Arbitrarily-Shaped Text Spotting with Point Gathering Network","paper":"/paper/pgnet-real-time-arbitrarily-shaped-text","first_author":"Pengfei Wang","n_authors":10,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/pgnet-real-time-arbitrarily-shaped-text"},"source":{"url":"https://arxiv.org/abs/2104.05458v1","title":"PGNet: Real-time Arbitrarily-Shaped Text Spotting with Point Gathering Network","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"Computer Vision","area_id":"computer-vision","collection":"Scene Text Models","url":"/methods/category/scene-text-models","pwc_aliases":[]}],"n_papers_tagged":2,"archive_num_papers":2,"papers_newest_first":[{"paper":null,"title":"Physics-informed generative neural network: an application to troposphere temperature prediction","date":"2021-07-08","arxiv_id":"2107.06991","n_code_links":0,"syntology":null},{"paper":"/paper/pgnet-real-time-arbitrarily-shaped-text","title":"PGNet: Real-time Arbitrarily-Shaped Text Spotting with Point Gathering Network","date":"2021-04-12","arxiv_id":"2104.05458","n_code_links":2,"syntology":null}],"papers_shown":2,"tasks":[{"task":"/task/decoder","name":"Decoder","papers":1},{"task":"/task/optical-character-recognition","name":"Optical Character Recognition (OCR)","papers":1},{"task":"/task/prediction","name":"Prediction","papers":1},{"task":"/task/scene-text-detection","name":"Scene Text Detection","papers":1},{"task":"/task/text-spotting","name":"Text Spotting","papers":1},{"task":"/task/time-series-1","name":"Time Series","papers":1},{"task":"/task/time-series","name":"Time Series Analysis","papers":1}],"tasks_shown":7,"n_tasks":7,"usage_by_year":[{"year":"2021","papers":2}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/pgnet"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}