With the rapid development of acquisition techniques and machine learning methods, data-driven visual computing has been receiving more and more attention in recent years. The main task of data-driven visual computing is aggregating information a large collection of images or models, learning semantic information from the collection and utilizing learned knowledge to support higher level tasks of understanding, processing, and even novel data generation. The generated or processed data, typically possessing semantic information, can be used to enrich the input data sets and enhance the learning tasks in future, forming a data-driven visual computing loop which can boost the emergence of "big visual data". In this course, we will talk about some recent developments of data-driven visual computing, from both graphics and vision community. Specifically, we will introduce the recent advances on image-driven smart image processing and manipulation, data-driven 3D shape analysis and modeling. We will also cover joint analysis and processing of 2D and 3D data.

Level

Intermediate

Prerequisites

Basic background in geometry processing and image processing. Basic working knowledge on data analysis and machine learning.

Intended Audience

Graduate students, practitioners, and researchers interested in geometry and image processing and, in particular, methods based on large data collections.

Presenter(s)

Kai Xu, National University of Defense Technology
Leonidas Guibas, Stanford University
Alexei Efros, UC Berkeley
Shimin Hu, Tsinghua University
Ariel Shamir, The Interdisciplinary Center
Siddhartha Chaudhuri, Cornell University
Jun-Yan Zhu, UC Berkeley

Kai Xu, National University of Defense Technology:
Kai Xu received his PhD in Computer Science at National University of Defense Technology (NUDT). He is currently a postdoctoral researcher at Shenzhen Institutes of Advanced Technology and also holds a faculty position at NUDT. During 2009 and 2010, he visited Simon Fraser University, supported by the Chinese government. His research interests include geometry processing and geometric modeling, especially topics involving large collections of 3D shapes and machine learning techniques. He serves as an associate editor for the Computers & Graphics journal (Elsevier). He has served on program committees for SGP, PG and GMP.

Leonidas Guibas, Stanford University:
Leonidas Guibas is a professor of computer science at Stanford University, where he heads the geometric computation group and is a member of the computer graphics and artificial intelligence laboratories. Guibas was a student of Donald Knuth at Stanford, where he received his Ph.D.in 1976.[1] He has worked for several industrial research laboratories, and joined the Stanford faculty in 1984. He was program chair for the ACM Symposium on Computational Geometry in 1996, is a Fellow of the ACM[3] and the IEEE, and was awarded the ACM–AAAI Allen Newell award for 2007.

Alexei Efros, UC Berkeley:
Alexei (Alyosha) Efros joined UC Berkeley in 2013 as associate professor of Electrical Engineering and Computer Science. Prior to that, he was nine years on the faculty of Carnegie Mellon University, and has also been affiliated with École Normale Supérieure/INRIA and University of Oxford. His research is in the area of computer vision and computer graphics, especially at the intersection of the two. He is particularly interested in using data-driven techniques to tackle problems which are very hard to model parametrically but where large quantities of data are readily available. Alyosha received his PhD in 2003 from UC Berkeley. He is a recipient of CVPR Best Paper Award (2006), NSF CAREER award (2006), Sloan Fellowship (2008), Guggenheim Fellowship (2008), Okawa Grant (2008), Finmeccanica Career Development Chair (2010), SIGGRAPH Significant New Researcher Award (2010), ECCV Best Paper Honorable Mention (2010), and the Helmholtz Test-of-Time Prize (2013).

Shimin Hu, Tsinghua University:
Shi-Min Hu is currently a professor in the Department of Computer Science and Technology, Tsinghua University, Beijing. He received Bachelor degree in Computational mathematics from Jilin University in 1990, the Master and PhD degree in Computational Geometry and Graphics from Zhejiang University in 1993 and 1996 respectively. His research interests include digital geometry processing, video processing, rendering, computer animation, and computer-aided geometric design, and he has published more than 100 papers in journals and peer-reviewed conferences, and hold over 30 patents. He currently serves as Associate Editor-in-Chief of The Visual Computer (Springer) and on the editorial board of IEEE Transactions on Visualization and Computer Graphics, Computer Aided Design (Elsevier), and Computer & Graphics (Elsevier). He has served as program chairs for various prestigious conferences, including Pacific Graphics, Geometric Modeling and Processing and Eurographics Symposium on Geometry Processing.

Ariel Shamir, The Interdisciplinary Center:
Ariel Shamir is a Professor at the school of Computer Science at the Interdisciplinary Center in Israel, where he is currently the vice-dean. Prof. Shamir received his Ph.D. in computer science in 2000 from the Hebrew University in Jerusalem. He spent two years at the center for computational visualization at the University of Texas in Austin. He was a visiting scientist at Mitsubishi Electric Research Labs in Cambridge MA (2006), Disney Research Boston, and MIT (2013). Prof. Shamir has numerous publications in journals and international refereed conferences, and a broad commercial experience working with, and consulting numerous companies including Mitsubishi Electric, Disney, PrimeSense (now Apple) and more. He is an associate editor for Computer Graphics Forum and Computers and Graphics journals. Prof. Shamir specializes in geometric modeling, computer graphics and machine learning.

Siddhartha Chaudhuri, Cornell University
Siddhartha Chaudhuri is a lecturer at Cornell University. He obtained his PhD from Stanford University in 2011, where he was supported by a Stanford Graduate Fellowship, and then conducted postdoctoral research at Princeton University. His research focuses on richer tools for visual content creation, particularly for novice and casual users, and on problems in 3D reconstruction and synthesis. This research is driven by a more abstract interest in shape understanding at both the structural and semantic levels. In the past, he has also worked on theoretical computational geometry and very large-scale real-time rendering systems. His work has been published at the top computer graphics and human-computer interaction conferences, and is also the basis for a commercial 3D modeling system.

Jun-Yan Zhu, UC Berkeley:
Jun-Yan Zhu received a BE degree with honors in computer science and technology from Tsinghua University in 2012. He is currently a PhD student at UC Berkeley in the Computer Science Division. His research interests include computer graphics, computer vision and computational photography. In particular, he is interested in summarizing, mining and exploring large-scale visual data collections, with the goal of building a digital bridge between humans and huge amounts of unorganized images and videos.