{"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/propagationnet-propagate-points-to-curve-to-1","title":"PropagationNet: Propagate Points to Curve to Learn Structure Information","arxiv_id":"2006.14308","date":"2020-06-25","proceeding":"CVPR 2020 6","authors":["Xiehe Huang","Weihong Deng","Haifeng Shen","Xiubao Zhang","Jieping Ye"],"abstract":"Deep learning technique has dramatically boosted the performance of face alignment algorithms. However, due to large variability and lack of samples, the alignment problem in unconstrained situations, \\emph{e.g}\\onedot large head poses, exaggerated expression, and uneven illumination, is still largely unsolved. In this paper, we explore the instincts and reasons behind our two proposals, \\emph{i.e}\\onedot Propagation Module and Focal Wing Loss, to tackle the problem. Concretely, we present a novel structure-infused face alignment algorithm based on heatmap regression via propagating landmark heatmaps to boundary heatmaps, which provide structure information for further attention map generation. Moreover, we propose a Focal Wing Loss for mining and emphasizing the difficult samples under in-the-wild condition. In addition, we adopt methods like CoordConv and Anti-aliased CNN from other fields that address the shift-variance problem of CNN for face alignment. When implementing extensive experiments on different benchmarks, \\emph{i.e}\\onedot WFLW, 300W, and COFW, our method outperforms state-of-the-arts by a significant margin. Our proposed approach achieves 4.05\\% mean error on WFLW, 2.93\\% mean error on 300W full-set, and 3.71\\% mean error on COFW.","url_abs":"https://arxiv.org/abs/2006.14308v1","url_pdf":"https://arxiv.org/pdf/2006.14308v1.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":[],"tasks":[{"task_slug":"face-alignment","task_name":"Face Alignment"}],"methods":[{"method_slug":"coordconv","method_name":"CoordConv"},{"method_slug":"heatmap","method_name":"Heatmap"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/face-alignment-on-300w","task":"Face Alignment","dataset":"300W","model":"PropNet","rank_in_archive_order":7,"of":48,"metrics":{"NME_inter-ocular (%, Challenge)":"3.99","NME_inter-ocular (%, Common)":"2.67","NME_inter-ocular (%, Full)":"2.93","NME_inter-pupil (%, Challenge)":"5.75","NME_inter-pupil (%, Common)":"3.7","NME_inter-pupil (%, Full)":"4.1"},"uses_additional_data":false},{"leaderboard":"/sota/face-alignment-on-cofw","task":"Face Alignment","dataset":"COFW","model":"PropNet","rank_in_archive_order":16,"of":28,"metrics":{"NME (inter-ocular)":"3.71%"},"uses_additional_data":false},{"leaderboard":"/sota/face-alignment-on-wflw","task":"Face Alignment","dataset":"WFLW","model":"PropNet","rank_in_archive_order":4,"of":36,"metrics":{"AUC@10 (inter-ocular)":"61.58","FR@10 (inter-ocular)":"2.96","NME (inter-ocular)":"4.05"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2006.14308","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}