philippos
 Philippos Mordohai
Postdoctoral Research Associate
Department of Computer Science
University of North Carolina at Chapel Hill

Office: Sitterson Hall 260
Phone Number: (919) 962 1965
E-mail: mordohai@cs.unc.edu




Home

Research

Publications

Teaching

Service, Awards and
Other Activities

CV (pdf)

 		EDUCATION
  • Ph.D. in Electrical Engineering with a minor in Finance and Business Economics at the University of Southern California (GPA 3.95)
  • Master of Science in Electrical Engineering at the University of Southern California. (GPA 3.92)
  • Diploma in Electrical and Computer Engineering at the Aristotle University of Thessaloniki, Greece. (GPA 8.14/10)

NEWS
I have started as a postdoc at UPenn. My new webpage is at www.seas.upenn.edu/~mordohai.

The slides for the short course entitled "Tensor Voting: A Perceptual Organization Approach to Computer Vision and Machine Learning" that I gave during CVPR 2007 are available here in ppt and pdf form. References to related work can also be downloaded as ppt and pdf.

Our demo: "Real-Time Video-Based Reconstruction of Urban Environments" by J.-M. Frahm, A. Akbarzadeh, P. Mordohai, B. Clipp, C. Engels, D. Gallup, P. Merrell, C. Salmi, S. Sinha, B. Talton, L. Wang, Q. Yang, H. Stewénius, H. Towles, G. Welch, R. Yang, D. Nistér and M. Pollefeys, won the Best Demo Award during CVPR 2007.

RESEARCH
Since September 2005, I have been a postdoctoral researcher at the Computer Science Department at the University of North Carolina, at Chapel Hill. I work with Marc Pollefeys mainly on 3D reconstruction from video sequences, as well as on some other projects related to multiple-view reconstruction.
Before coming to UNC, I spent five years pursuing my Ph.D. at the Institute for Robotics and Intelligent Systems at the University of Southern California. My research focused on the development of a perceptual organization approach for computational stereo vision and machine learning under the guidance of Gérard Medioni.

The research areas I am most interested in are:
  • Binocular and multiple-view stereo
  • Video-based 3D reconstruction
  • Perceptual organization
  • Machine learning

CURRENT RESEARCH PROJECTS
  • UrbanScape: Since September 2005 I have worked on the DARPA UrbanScape project, which aims at the real-time 3-D reconstruction of urban scenes from multiple video streams captured from a moving vehicle. I contribute mainly in modules that address dense 3D reconstruction, such as the stereo engine, the fusion of depthmaps within and across video streams and the generation of the final 3D model. More details on UrbanScape can be found on my research page and the main Urban 3D Modelling from Video webpage that describes the video-based part of UrbanScape that is carried out by the UNC computer vision group led by Marc Pollefeys and the computer vision group from the Center for Visualization and Virtual Environments of the University of Kentucky led by David Nistér.

  • VACE: I have also started working on a new project entitled "3D Content Extraction from Video Streams". It is part of the DTO Video Analysis and Content Extraction program. We work in collaboration with David's Nistér's group to develop algorithms that can automatically extract 3D information from videos captured by unknown cameras under unknown conditions.

  • Multiple-View Reconstruction: I am also involved in a few projects that address multiple-view reconstruction from different angles.

3DPVT 2006
I was the chair of local organization of the Third International Symposium on 3D Data Processing, Visualization and Transmission which was held in Chapel Hill between the 14th and 16th of June 2006. The symposium included 28 refereed oral presentations, 109 refereed posters, 6 keynote presentations by distinguished representatives from both academia and the industry and was attended by approximately 230 people.

COMPUTER VISION MEETING
Continuing the tradition I started at USC, I organize the weekly Computer Vision meeting. Send me an e-mail if you are interested in presenting your work.

FACE MODEL
I spent a few years demonstrating and evaluating 3D face reconstruction and recognition using technology developed by Geometrix, Inc.


For a 3-D model of my face using these two pictures click on the pictures or here. This model was created with the Facevision 200 Series system.