{"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/pose-invariant-face-alignment-with-a-single","title":"Pose-Invariant Face Alignment with a Single CNN","arxiv_id":"1707.06286","date":"2017-07-19","proceeding":"ICCV 2017 10","authors":["Amin Jourabloo","Mao Ye","Xiaoming Liu","Liu Ren"],"abstract":"Face alignment has witnessed substantial progress in the last decade. One of\nthe recent focuses has been aligning a dense 3D face shape to face images with\nlarge head poses. The dominant technology used is based on the cascade of\nregressors, e.g., CNN, which has shown promising results. Nonetheless, the\ncascade of CNNs suffers from several drawbacks, e.g., lack of end-to-end\ntraining, hand-crafted features and slow training speed. To address these\nissues, we propose a new layer, named visualization layer, that can be\nintegrated into the CNN architecture and enables joint optimization with\ndifferent loss functions. Extensive evaluation of the proposed method on\nmultiple datasets demonstrates state-of-the-art accuracy, while reducing the\ntraining time by more than half compared to the typical cascade of CNNs. In\naddition, we compare multiple CNN architectures with the visualization layer to\nfurther demonstrate the advantage of its utilization.","url_abs":"http://arxiv.org/abs/1707.06286v1","url_pdf":"http://arxiv.org/pdf/1707.06286v1.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"},{"task_slug":"facial-landmark-detection","task_name":"Facial Landmark Detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/facial-landmark-detection-on-300w","task":"Facial Landmark Detection","dataset":"300W","model":"Pose-Invariant","rank_in_archive_order":13,"of":15,"metrics":{"NME":"6.30"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}