Group-valued regularization for analysis of articulated motion LNCS Rosman, Guy Bronstein, Alexander ; https://orcid.org/0000-0001-9699-8730 Bronstein, Michael M. Tai, Xue-Cheng Kimmel, Ron We present a novel method for estimation of articulated motion in depth scans. The method is based on a framework for regularization of vector- and matrix- valued functions on parametric surfaces. We extend augmented-Lagrangian total variation regularization to smooth rigid motion cues on the scanned 3D surface obtained from a range scanner. We demonstrate the resulting smoothed motion maps to be a powerful tool in articulated scene understanding, providing a basis for rigid parts segmentation, with little prior assumptions on the scene, despite the noisy depth measurements that often appear in commodity depth scanners. Springer Nature 2012 info:eu-repo/semantics/conferenceObject doc-type:conferenceObject text http://purl.org/coar/resource_type/c_5794 https://research-explorer.ista.ac.at/record/18348 Rosman G, Bronstein AM, Bronstein MM, Tai X-C, Kimmel R. Group-valued regularization for analysis of articulated motion. In: <i>Computer Vision, ECCV 2012 - Workshops and Demonstrations</i>. Vol 7583. Springer Nature; 2012:52-62. doi:<a href="https://doi.org/10.1007/978-3-642-33863-2_6">10.1007/978-3-642-33863-2_6</a> eng info:eu-repo/semantics/altIdentifier/doi/10.1007/978-3-642-33863-2_6 info:eu-repo/semantics/altIdentifier/issn/0302-9743 info:eu-repo/semantics/altIdentifier/e-issn/1611-3349 info:eu-repo/semantics/altIdentifier/isbn/9783642338625 info:eu-repo/semantics/altIdentifier/e-isbn/9783642338632 info:eu-repo/semantics/closedAccess