{"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/egocap-egocentric-marker-less-motion-capture-1","title":"EgoCap: Egocentric Marker-less Motion Capture with Two Fisheye Cameras","arxiv_id":"1609.07306","date":"2016-09-23","proceeding":null,"authors":["Helge Rhodin","Christian Richardt","Dan Casas","Eldar Insafutdinov","Mohammad Shafiei","Hans-Peter Seidel","Bernt Schiele","Christian Theobalt"],"abstract":"Marker-based and marker-less optical skeletal motion-capture methods use an\noutside-in arrangement of cameras placed around a scene, with viewpoints\nconverging on the center. They often create discomfort by possibly needed\nmarker suits, and their recording volume is severely restricted and often\nconstrained to indoor scenes with controlled backgrounds. Alternative\nsuit-based systems use several inertial measurement units or an exoskeleton to\ncapture motion. This makes capturing independent of a confined volume, but\nrequires substantial, often constraining, and hard to set up body\ninstrumentation. We therefore propose a new method for real-time, marker-less\nand egocentric motion capture which estimates the full-body skeleton pose from\na lightweight stereo pair of fisheye cameras that are attached to a helmet or\nvirtual reality headset. It combines the strength of a new generative pose\nestimation framework for fisheye views with a ConvNet-based body-part detector\ntrained on a large new dataset. Our inside-in method captures full-body motion\nin general indoor and outdoor scenes, and also crowded scenes with many people\nin close vicinity. The captured user can freely move around, which enables\nreconstruction of larger-scale activities and is particularly useful in virtual\nreality to freely roam and interact, while seeing the fully motion-captured\nvirtual body.","url_abs":"http://arxiv.org/abs/1609.07306v1","url_pdf":"http://arxiv.org/pdf/1609.07306v1.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":"pose-estimation","task_name":"Pose Estimation"},{"task_slug":"two","task_name":"Vocal Bursts Valence Prediction"}],"methods":[],"datasets_introduced":[{"slug":"egocap","name":"EgoCap","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}