Seminar by Mr. Hao Su

Title: ShapeNet: a Large-scale 3D Shape Collection for Geometry and Image Understanding Date and Time: 9:00am-10:00am, Wednesday, August 26, 2015 Venue: Room 146 Research Building

Speaker: Mr. Hao Su
Date and Time: 9:00am-10:00am, Wednesday, August 26, 2015.
Venue: Room 146 Research Building

Title: ShapeNet: a Large-scale 3D Shape Collection for Geometry and Image Understanding


Recent technological developments have led to an explosion in the amount of 3D data. We believe that organizing such data and labeling them to be a knowledge base is beneficial, since we live a world where 3D is the natural space. With this background, we are building a large-scale 3D shape repository called ShapeNet , containing millions  of  CAD models from thousands of object classes with rich annotations.
ShapeNet is especially important for solving computer vision problems. Essentially, knowledge stored in ShapeNet can be used as geometry and appearance priors for understanding 2D images. Following this idea, we jointly analyze 3D models and 2D images for various purposes, including single image depth estimation , training  data synthesis  for CNN learning, and shape-centric  image representations.
Hao Su is currently a Ph.D student in the Computer Science Department of Stanford University, advised by Prof. Leonidas J. Guibas, co-advised by Prof. Silvio Savarese.
He is a member of Artificial Intelligence Lab and Geometric Computing Lab. He has also completed his Ph.D degree from School of Mathematics and Systems Science from Beihang University, China, specialized in statistics.
Hao's research interest includes computer vision, machine learning and geometry processing. In particular, he works on techniques for joint analysis of 2D images and 3D shapes by deep learning and manifold learning methods ,to enable information transportation between image and shape world.  He has publications in CVPR, ICCV, NIPS, ICML, SIGGRAPH, SIGGRAPH Asia, VLDB, SIGSPATIAL, IJCV, etc.
 He is a reviewer of CVPR, ICCV, TPAMI, TIP, NIPS, SIGGRAPH, EUROGRAPHICS, PG, Science China, etc. He also co-chaired CVPR workshop 3DSI'15 and ICCV workshop 3dRR'15.
Prior to joining Prof. Guibas' group, he was advised by Prof. Fei-Fei Li from 2008 to 2012, advised by Dr. Harry Shum  and  Dr. Jian Sun  at MSRA from 2005 to 2008.