{"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/plane-geometry-diagram-parsing","title":"Plane Geometry Diagram Parsing","arxiv_id":"2205.09363","date":"2022-05-19","proceeding":null,"authors":["Ming-Liang Zhang","Fei Yin","Yi-Han Hao","Cheng-Lin Liu"],"abstract":"Geometry diagram parsing plays a key role in geometry problem solving, wherein the primitive extraction and relation parsing remain challenging due to the complex layout and between-primitive relationship. In this paper, we propose a powerful diagram parser based on deep learning and graph reasoning. Specifically, a modified instance segmentation method is proposed to extract geometric primitives, and the graph neural network (GNN) is leveraged to realize relation parsing and primitive classification incorporating geometric features and prior knowledge. All the modules are integrated into an end-to-end model called PGDPNet to perform all the sub-tasks simultaneously. In addition, we build a new large-scale geometry diagram dataset named PGDP5K with primitive level annotations. Experiments on PGDP5K and an existing dataset IMP-Geometry3K show that our model outperforms state-of-the-art methods in four sub-tasks remarkably. Our code, dataset and appendix material are available at https://github.com/mingliangzhang2018/PGDP.","url_abs":"https://arxiv.org/abs/2205.09363v1","url_pdf":"https://arxiv.org/pdf/2205.09363v1.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":"plane-geometry-diagram-parsing","repo_url":"https://github.com/mingliangzhang2018/PGDP","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"geometry-problem-solving","task_name":"Geometry Problem Solving"},{"task_slug":"graph-neural-network","task_name":"Graph Neural Network"},{"task_slug":"instance-segmentation","task_name":"Instance Segmentation"},{"task_slug":"mathematical-question-answering","task_name":"Mathematical Question Answering"},{"task_slug":null,"task_name":"Relation"},{"task_slug":"scene-parsing","task_name":"Scene Parsing"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[{"method_slug":"graph-neural-network","method_name":"Graph Neural Network"}],"datasets_introduced":[{"slug":"pgdp5k","name":"PGDP5K","full_name":"Plane Geometry Diagram Parsing Dataset"}],"methods_introduced":[],"results":[{"leaderboard":"/sota/mathematical-question-answering-on-geometry3k","task":"Mathematical Question Answering","dataset":"Geometry3K","model":"PGDPNet","rank_in_archive_order":3,"of":8,"metrics":{"Accuracy (%)":"74.1"},"uses_additional_data":false},{"leaderboard":"/sota/scene-parsing-on-pgdp5k","task":"Scene Parsing","dataset":"PGDP5K","model":"PGDPNet","rank_in_archive_order":1,"of":2,"metrics":{"Total Accuracy":"84.7"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2205.09363","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.09363"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mingliangzhang2018/PGDP","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":1,"unverified":2},"by_repo_kind":{"official":{"samples":3,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"e261fa29066b37e5","entry":"smooth_l1_loss","repo":"mingliangzhang2018/PGDP","repo_kind":"official","path":"geo_parse/layers/smooth_l1_loss.py","file_url":"https://github.com/mingliangzhang2018/PGDP/blob/HEAD/geo_parse/layers/smooth_l1_loss.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e261fa29066b37e5"}},{"code_sha256_prefix":"2902bf4410253ff7","entry":"interpolate","repo":"mingliangzhang2018/PGDP","repo_kind":"official","path":"geo_parse/layers/misc.py","file_url":"https://github.com/mingliangzhang2018/PGDP/blob/HEAD/geo_parse/layers/misc.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2902bf4410253ff7"}},{"code_sha256_prefix":"426fd02a2beaf826","entry":"sigmoid_focal_loss_cpu","repo":"mingliangzhang2018/PGDP","repo_kind":"official","path":"geo_parse/layers/sigmoid_focal_loss.py","file_url":"https://github.com/mingliangzhang2018/PGDP/blob/HEAD/geo_parse/layers/sigmoid_focal_loss.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"426fd02a2beaf826"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}