{"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/capturing-hands-in-action-using","title":"Capturing Hands in Action using Discriminative Salient Points and Physics Simulation","arxiv_id":"1506.02178","date":"2015-06-06","proceeding":null,"authors":["Dimitrios Tzionas","Luca Ballan","Abhilash Srikantha","Pablo Aponte","Marc Pollefeys","Juergen Gall"],"abstract":"Hand motion capture is a popular research field, recently gaining more\nattention due to the ubiquity of RGB-D sensors. However, even most recent\napproaches focus on the case of a single isolated hand. In this work, we focus\non hands that interact with other hands or objects and present a framework that\nsuccessfully captures motion in such interaction scenarios for both rigid and\narticulated objects. Our framework combines a generative model with\ndiscriminatively trained salient points to achieve a low tracking error and\nwith collision detection and physics simulation to achieve physically plausible\nestimates even in case of occlusions and missing visual data. Since all\ncomponents are unified in a single objective function which is almost\neverywhere differentiable, it can be optimized with standard optimization\ntechniques. Our approach works for monocular RGB-D sequences as well as setups\nwith multiple synchronized RGB cameras. For a qualitative and quantitative\nevaluation, we captured 29 sequences with a large variety of interactions and\nup to 150 degrees of freedom.","url_abs":"http://arxiv.org/abs/1506.02178v4","url_pdf":"http://arxiv.org/pdf/1506.02178v4.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":"capturing-hands-in-action-using","repo_url":"https://github.com/dimtziwnas/HandObjectInteractionIJCV16_HandMotionViewer","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"capturing-hands-in-action-using","repo_url":"https://github.com/dimtziwnas/HandObjectInteractionIJCV16_GroundTruthViewer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[],"datasets_introduced":[{"slug":"hic","name":"HIC","full_name":"Hands in Action"}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1506.02178","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}