BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Dynamic Scene 3D Reconstruction
DTSTART:20141014T140000
DTEND:20141014T150000
DTSTAMP:20260501T055540Z
UID:f81a41e35f5987233f73c708b22eb784c34ff523d92d0e87e9380753
CATEGORIES:Conferences - Seminars
DESCRIPTION:Prof. Kun Li\, B.E. Beijing University of Posts and Telecommun
 ications\, Beijing\, 2006\,  Master and Ph.D. from Tsinghua University\, 
 Beijing\, 2011. She is currently working as an Assistant Professor at Scho
 ol of Computer Science and Technology\, Tianjin University\, China. Her re
 search interests include image/video processing\, image-based modeling\, d
 ynamic scene 3-D reconstruction\, and motion capture.\nDynamic scene 3-D r
 econstruction is a hot issue in computer vision and graphics. We built a m
 ulti-camera dome system to capture multi-view videos of an actor\, and rec
 onstructed the shape and motion at each time instant. We generated depth m
 aps by solving a proposed variational model\, which is regularized by four
  constraints to ensure the accuracy and completeness of the reconstruction
 . The depths of all the views are merged together to generate a complete 3
 -D mesh. Finally\, taking this 3-D mesh as the underlying scene representa
 tion\, we apply an iterative volumetric Laplacian deformation framework wi
 th a new positional-constraint computation scheme to extract the 3D motion
  information from the multi-view video sequences and generate time-varying
  shapes. We also propose a temporal-dense dynamic 3-D reconstruction metho
 d with low frame rate cameras. In this talk\, I will also introduce severa
 l other research work of mine\, including non-rigid structure from motion\
 , depth optimization\, photorealistic animation and 3-D print for human.
LOCATION:BC 129 https://plan.epfl.ch/?room==BC%20129
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR