Danielle Ezuz (CS, Technion)
Thursday, 16.5.2019, 10:30
Shape correspondence is a fundamental task in shape analysis, with a variety of applications in computer graphics and computer vision. Example applications include statistical shape interpolation, texture, segmentation and deformation transfer, and application of deep learning to 3D shapes. Formulating the desired geometric properties of the correspondence is a challenging task, as the quality of the result can be easily evaluated by a human observer, yet is challenging to quantify. Additionally, the desired properties of the result highly depend on the downstream application, that should be taken into account to reliably evaluate shape correspondence.
In this talk I will give an overview of the problem, and will present recent methods for computation of shape correspondence between non isometric shapes. I will also discuss applications of shape correspondence, such as 3D shape classification and retrieval using deep learning.