{"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/learning-to-find-eye-region-landmarks-for","title":"Learning to Find Eye Region Landmarks for Remote Gaze Estimation in Unconstrained Settings","arxiv_id":"1805.04771","date":"2018-05-12","proceeding":null,"authors":["Seonwook Park","Xucong Zhang","Andreas Bulling","Otmar Hilliges"],"abstract":"Conventional feature-based and model-based gaze estimation methods have\nproven to perform well in settings with controlled illumination and specialized\ncameras. In unconstrained real-world settings, however, such methods are\nsurpassed by recent appearance-based methods due to difficulties in modeling\nfactors such as illumination changes and other visual artifacts. We present a\nnovel learning-based method for eye region landmark localization that enables\nconventional methods to be competitive to latest appearance-based methods.\nDespite having been trained exclusively on synthetic data, our method exceeds\nthe state of the art for iris localization and eye shape registration on\nreal-world imagery. We then use the detected landmarks as input to iterative\nmodel-fitting and lightweight learning-based gaze estimation methods. Our\napproach outperforms existing model-fitting and appearance-based methods in the\ncontext of person-independent and personalized gaze estimation.","url_abs":"http://arxiv.org/abs/1805.04771v1","url_pdf":"http://arxiv.org/pdf/1805.04771v1.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":"learning-to-find-eye-region-landmarks-for","repo_url":"https://github.com/Joey0094/GazeML_torch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"learning-to-find-eye-region-landmarks-for","repo_url":"https://github.com/Joey0094/HRNetGaze_torch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"gaze-estimation","task_name":"Gaze Estimation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1805.04771","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}