The last decade has witnessed the exciting development of efficient edge-aware filtering (EAF) techniques, stemming from different theories and principles. Thanks to their power in adaptively dealing with various visual signals as well as significant computational and implementation advantages, these new image filtering techniques have found a great variety of applications in image processing, computer vision and computer graphics. These applications range from the classical image denoising task to semantic image segmentation and labeling. In this talk, we will first present various state-of-the-art nonlinear EAF techniques, while revealing theoretical connections, new insights and generalization. Representative applications of these filtering techniques will be illustrated and discussed. We will discuss a serious computational challenge faced by most cost volume filtering-based approaches, i.e. the curse of the huge discrete space in labeling problems. We will present our works to tackle this challenge using randomized hypothesis or importance sampling, and propagation approach on the label space. Finally, we present a fast approximated solver for an edge-aware filtering that is formulated as a global optimization problem. Our resulting methods achieve state-of-the-art performance at 10-100 times speedup.
Minh N. Do is a Professor in the Department of Electrical and Computer Engineering at the University of Illinois at Urbana-Champaign (UIUC). He received the B.Eng. degree in Computer Engineering from the University of Canberra, Australia in 1997, and the Dr.Sci. degree in Communication Systems from the Swiss Federal Institute of Technology Lausanne (EPFL), Switzerland in 2001. Since 2002, he has been on the faculty of the Department of Electrical and Computer Engineering at UIUC, and holds joint appointments with the Coordinated Science Laboratory, the Beckman Institute for Advanced Science and Technology, the Advanced Digital Sciences Center, and the Department of Bioengineering. His work covers image and multi-dimensional signal processing, wavelets and multiscale geometric analysis, computational imaging, and visual information representation, and has led to more than 50 journal papers, 100 conference papers, and 20000 Google Scholar citations. He received a Silver Medal from the 32nd International Mathematical Olympiad in 1991, a University Medal from the University of Canberra in 1997, a Doctorate Award from the EPFL in 2001, a CAREER Award from the National Science Foundation in 2003, a Xerox Award for Faculty Research from the UIUC College of Engineering in 2007, and a Young Author Best Paper Award from IEEE in 2008. He was an Associate Editor of the IEEE Transactions on Image Processing, and a member of the IEEE Technical Committees on Signal Processing Theory and Methods, and on Image, Video, and Multidimensional Signal Processing. He was elected as an IEEE Fellow for his contributions to image representation and computational imaging. He was a co-founder and CTO of Personify Inc., a spin-off from UIUC to commercialize depth-based visual communication.