Assistant Professor of Electrical and Computer Engineering
New York University
Tuesday May 6
Advances in informatics technologies coupled with data acquisition techniques have resulted in the production of three dimensional (3D) models at an unprecedented scale across areas as diverse as engineering, science and medicine. We are therefore faced with a dramatic demand for automatic 3D model processing, understanding and analyzing techniques. Researchers are regularly interested in interpreting the 3D shape of such models according to their intrinsic geometric attributes. The effective and efficient interpretation of 3D models is often challenged with the prevalence of non-rigidity within the shapes, the corruption of the shapes due to the presence of geometric noise, and the availability of a large volume of 3D models in innumerable databases. The presented work is concentrated on the development of a novel framework for 3D shape analysis, such as shape matching, segmentation, and retrieval, based on the effective utilization of the heat diffusion concept. The novelty of this framework is derived from an analogy between the process of 3D shape interpretation and that of heat transfer. The approaches exploit the intelligence of heat as a global structure-aware message that traverses across a meshed surface and is capable of exploring the intrinsic geometric features of the shape. We have demonstrated the performance of several heat diffusion based approaches within above framework for efficient non-rigid 3D shape registration, robust segmentation of 3D models, and efficient retrieval of 3D models with applications in engineering, medicine and biology. The experimental results indicate that heat diffusion approaches are able to reveal the interpretations of 3D shape in a highly robust fashion, independent of any reference to prior knowledge, and in a manner consistent to human perception. In addition, the heat diffusion approaches are very general and have great potential for applications to a broad range of research fields, for example, 3D urban modeling for the design of smart city, 3D medical image processing for the diagnosis of disease, and social media.
Yi Fang is an Assistant Professor of Electrical & Computer Engineering, New York University in Abu Dhabi. He received his Ph.D. in Engineering from Purdue University, West Lafayette, USA, in December 2011. He worked as research intern in Siemens Corporate Research on 3D medical image processing. He then joined Riverain Technologies, a leader and technology innovator in the healthcare industry and beyond, as a Senior Research Scientist. His current research interests are in computer graphics, computer vision, image processing, and machine learning and their applications to multiple disciplines as diverse as engineering, medicine, biology, and social science. He has co-authored 20 refereed papers for journals and top tier conferences, of which he is the first author in nine. Some of his works have been widely reported by both national and international media, such as Purdue Newsroom, ScienceDaily, and Yahoo!
Host: Ruigang Yang