2013 Poster Sessions : Exploring Image Relationships Using Functional Maps

Student Name : Fan Wang
Advisor : Leo Guibas
Research Areas: Graphics/HCI
Establishing correspondences between images is challenging, especially when point-to-point matching is hard to obtain due to large variability in object appearances. Instead of computing point-based correspondences between images, we find functional maps between them which can act as information transporters between the images. Functional maps are based on correspondences between local properties or attributes defined over images, and can be found efficiently by solving a linear system. After introducing this functional framework, we explore its efficacy using the application of segmentation transfer. Functional maps are used to transfer segmentation from a set of training images to a test image, with results that match or improve other state-of-the-art methods.

Fan Wang is a 4th year PhD student in Department of Electrical Engineering. She is now advised by Professor Leonidas Guibas in Geometric Computing group, and works on computer vision methods. Her current projects are mainly focused on joint image segmentation and understanding.