{"615173":{"#nid":"615173","#data":{"type":"event","title":"PhD Proposal by Zhaoyang Lv","body":[{"value":"\u003Cp\u003E\u003Cstrong\u003ETitle: Visual Dense Three-Dimensional Motion Estimation in the Wild\u003C\/strong\u003E\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cstrong\u003EDate\u003C\/strong\u003E: Wednesday, December 12, 2018\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cstrong\u003ETime\u003C\/strong\u003E: 10:00 am to 11:30 am (EST)\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cstrong\u003ELocation\u003C\/strong\u003E: GVU cafe, TSRB\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\r\n\r\n\u003Cp\u003EZhaoyang Lv\u003C\/p\u003E\r\n\r\n\u003Cp\u003ESchool of Interactive Computing, College of Computing\u003C\/p\u003E\r\n\r\n\u003Cp\u003EGeorgia Institute of Technology\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Ca href=\u0022https:\/\/www.cc.gatech.edu\/~zlv30\/\u0022\u003Ehttps:\/\/www.cc.gatech.edu\/~zlv30\/\u003C\/a\u003E\u0026nbsp;\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cstrong\u003ECommittee:\u0026nbsp;\u003C\/strong\u003E\u003C\/p\u003E\r\n\r\n\u003Cp\u003EDr. James\u003Cbr \/\u003E\r\nM. Rehg (Advisor, School of Interactive Computing, Georgia\u003Cbr \/\u003E\r\nInstitute of Technology)\u003C\/p\u003E\r\n\r\n\u003Cp\u003EDr. Frank\u003Cbr \/\u003E\r\nDellaert (Co-Advisor, School of Interactive Computing, Georgia\u003Cbr \/\u003E\r\nInstitute of Technology)\u003C\/p\u003E\r\n\r\n\u003Cp\u003EDr. James\u003Cbr \/\u003E\r\nHays (School of Interactive Computing, Georgia\u003Cbr \/\u003E\r\nInstitute of Technology)\u003C\/p\u003E\r\n\r\n\u003Cp\u003EDr. Zsolt\u003Cbr \/\u003E\r\nKira (School of Interactive Computing, Georgia\u003Cbr \/\u003E\r\nInstitute of Technology; Georgia Tech Research\u003Cbr \/\u003E\r\nInstitute)\u003C\/p\u003E\r\n\r\n\u003Cp\u003EDr. Andreas\u003Cbr \/\u003E\r\nGeiger (Autonomous Vision Group, Max Planck Institute Intelligent System;\u003Cbr \/\u003E\r\nUniversity of Tuebingen)\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cstrong\u003EAbstract:\u0026nbsp;\u003C\/strong\u003E\u003C\/p\u003E\r\n\r\n\u003Cp\u003EOne of the most fundamental ability of the human perception system is to seamlessly sense the changing 3D worlds from our ego-centric visual observations. Driven by the modern applications of robotics, autonomous driving, and mixed reality, the machine perception requires a precise dense representation of 3D motion with low latency. In this thesis, I focus on the task of estimating absolute 3D motions in world coordinate in unconstrained environments from ego-centric visual information only. The goal is to achieve a fast algorithm that can produce a dense\u0026nbsp;and accurate representation of the 3D motions.\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\r\n\r\n\u003Cp\u003ETo achieve this goal, I propose to investigate the problem from four perspectives with the following contributions:\u003C\/p\u003E\r\n\r\n\u003Cp\u003E1) Present a fast and accurate continuous optimization approach that solves the 3D scene motions as moving fixed-a-priori planar segments.\u003C\/p\u003E\r\n\r\n\u003Cp\u003E2) Present a learning-based approach that recovers the dense scene flow from ego-centric motion and optical flow, decomposed by a novel data-driven rigidity prediction.\u0026nbsp;\u003C\/p\u003E\r\n\r\n\u003Cp\u003E3) Present a modern synthesis of the classic inverse compositional method for 3D rigid motion estimation using dense image alignment.\u003C\/p\u003E\r\n\r\n\u003Cp\u003E4) I will propose a novel object-centric scene flow representation incorporating top-down recognition. Specifically, scene flow of each instance composes 3D rigid motion basis and local deformation field. The proposed approach will progressively predict local deformation of the rigid instance motion to align the instance across views.\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\r\n","summary":null,"format":"limited_html"}],"field_subtitle":"","field_summary":"","field_summary_sentence":[{"value":"Visual Dense Three-Dimensional Motion Estimation in the Wild"}],"uid":"27707","created_gmt":"2018-12-10 14:06:29","changed_gmt":"2018-12-10 14:06:29","author":"Tatianna Richardson","boilerplate_text":"","field_publication":"","field_article_url":"","field_event_time":{"event_time_start":"2018-12-12T10:00:00-05:00","event_time_end":"2018-12-12T12:00:00-05:00","event_time_end_last":"2018-12-12T12:00:00-05:00","gmt_time_start":"2018-12-12 15:00:00","gmt_time_end":"2018-12-12 17:00:00","gmt_time_end_last":"2018-12-12 17:00:00","rrule":null,"timezone":"America\/New_York"},"extras":[],"groups":[{"id":"221981","name":"Graduate Studies"}],"categories":[],"keywords":[{"id":"102851","name":"Phd proposal"}],"core_research_areas":[],"news_room_topics":[],"event_categories":[{"id":"1788","name":"Other\/Miscellaneous"}],"invited_audience":[{"id":"78771","name":"Public"},{"id":"174045","name":"Graduate students"},{"id":"78751","name":"Undergraduate students"}],"affiliations":[],"classification":[],"areas_of_expertise":[],"news_and_recent_appearances":[],"phone":[],"contact":[],"email":[],"slides":[],"orientation":[],"userdata":""}}}