{"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/holistically-attracted-wireframe-parsing","title":"Holistically-Attracted Wireframe Parsing","arxiv_id":"2003.01663","date":"2020-03-03","proceeding":"CVPR 2020 6","authors":["Nan Xue","Tianfu Wu","Song Bai","Fu-Dong Wang","Gui-Song Xia","Liangpei Zhang","Philip H. S. Torr"],"abstract":"This paper presents a fast and parsimonious parsing method to accurately and robustly detect a vectorized wireframe in an input image with a single forward pass. The proposed method is end-to-end trainable, consisting of three components: (i) line segment and junction proposal generation, (ii) line segment and junction matching, and (iii) line segment and junction verification. For computing line segment proposals, a novel exact dual representation is proposed which exploits a parsimonious geometric reparameterization for line segments and forms a holistic 4-dimensional attraction field map for an input image. Junctions can be treated as the \"basins\" in the attraction field. The proposed method is thus called Holistically-Attracted Wireframe Parser (HAWP). In experiments, the proposed method is tested on two benchmarks, the Wireframe dataset, and the YorkUrban dataset. On both benchmarks, it obtains state-of-the-art performance in terms of accuracy and efficiency. For example, on the Wireframe dataset, compared to the previous state-of-the-art method L-CNN, it improves the challenging mean structural average precision (msAP) by a large margin ($2.8\\%$ absolute improvements) and achieves 29.5 FPS on single GPU ($89\\%$ relative improvement). A systematic ablation study is performed to further justify the proposed method.","url_abs":"https://arxiv.org/abs/2003.01663v1","url_pdf":"https://arxiv.org/pdf/2003.01663v1.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":"holistically-attracted-wireframe-parsing","repo_url":"https://github.com/cherubicXN/hawp","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":null,"task_name":"GPU"},{"task_slug":"line-segment-detection","task_name":"Line Segment Detection"},{"task_slug":"wireframe-parsing","task_name":"Wireframe Parsing"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/line-segment-detection-on-york-urban-dataset","task":"Line Segment Detection","dataset":"York Urban Dataset","model":"HAWP","rank_in_archive_order":9,"of":16,"metrics":{"FH":"66.3","sAP10":"28.5","sAP15":"29.7","sAP5":"26.1"},"uses_additional_data":false},{"leaderboard":"/sota/line-segment-detection-on-wireframe-dataset","task":"Line Segment Detection","dataset":"wireframe dataset","model":"HAWP","rank_in_archive_order":4,"of":10,"metrics":{"FH":"83.1","sAP10":"66.5","sAP15":"68.2","sAP5":"62.5"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2003.01663","atlas_url":"https://app.syntology.ai/?focus=2003.01663","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}