:Back    
Export: PDF | Excel | Word

Jan-Michael Frahm

Title: Associate Professor, Computer Science
Department/School: Computer Science , CB#3175
Telephone: (919) 590-6003
Email:frahm@email.unc.edu
Webpage:www.cs.unc.edu/~jmf
Appointed Year: 2007
Education:• PHD Computer Science , Christian Albrechts University Kiel 2005
Languages:• German (native/bilingual proficiency)
Specialization:Computer Vision, Augmented and Virtual Reality and related areas
Relevant Experience:• 2014 Associate Professor at University of North Carolina at Chapel Hill
• 2011-2013 Assistant Professor at University of North Carolina at Chapel Hill
• 2007-2011 Research Assistant at University of North Carolina at Chapel Hill
• 2005-2007 Postdoc at University of North Carolina at Chapel Hill
Dissertations and Theses Supervised in Past 5 Years: 7
Relevant Courses Taught:• COMP 550 Algorithms and Analysis
• COMP 776 Computer Vision
• COMP 876 Advanced Topics in Computer Vision
Recent Publications:• 2016 Structure-from-motion revisited, JL Schonberger, JM Frahm, IEEE Conference on Computer Vision and Pattern Recognition
• 2015 Reconstructing the world* in six days*(as captured by the yahoo 100 million image dataset), J Heinly, JL Schonberger, E Dunn, JM Frahm, IEEE Conference on Computer Vision and Pattern Recognition
• 2013 USAC: a universal framework for random sample consensus R Raguram, O Chum, M Pollefeys, J Matas, JM Frahm, IEEE Transactions on Pattern Analysis and Machine Intelligence
• 2012 Feature tracking and matching in video using programmable graphics hardware SN Sinha, JM Frahm, M Pollefeys, Y Genc, Machine Vision and Applications
• 2012 Comparative evaluation of binary features, J Heinly, E Dunn, JM Frahm, European Conference on Computer Vision
• 2010 Building rome on a cloudless day JM Frahm, P Fite-Georgel, D Gallup, T Johnson, R Raguram, C Wu, ... European Conference on Computer Vision
• 2009 From structure-from-motion point clouds to fast location recognition A Irschara, C Zach, JM Frahm, H Bischof, IEEE Computer Vision and Pattern Recognition, 2009
• 2008 A comparative analysis of RANSAC techniques leading to adaptive real-time random sample consensus, R Raguram, JM Frahm, M Pollefeys, European Conference on Computer Vision
• 2008 Modeling and recognition of landmark image collections using iconic scene graphs X Li, C Wu, C Zach, S Lazebnik, JM Frahm, European Conference on Computer Vision
• 2006 RANSAC for (quasi-) degenerate data (QDEGSAC) JM Frahm, M Pollefeys, IEEE Computer Vision and Pattern Recognition, 2006

SEARCH FACULTY
  KEYWORDS:
    

 
  NAME:
 
  REGION:
 
  LANGUAGE:
 
  [CLEAR]  
  1. Searches are not case-sensitive.
  2. Enclosing two or more words in double quotes will return only faculty profiles containing the quoted terms in the requested order (e.g. a search for "Public Health" will only return faculty profiles that contain the phrase 'Public Health'.)
  3. Use 'AND' in keyword box to search for words that appear in any order in a faculty profile (e.g. a search for 'Public AND Health' will return faculty profiles that contain both the individual words 'Public' and 'Health.')
  4. Using 'OR' in keyword box will broaden your search by returning faculty profiles that contain keywords on either side of the word 'OR' (e.g. a search for 'Public OR Health' will return faculty profiles that contain either one or both of the words 'Public' and 'Health.' )
  5. A shortened form of your keyword will further broaden your search (e.g. a search for 'demo' will return faculty profiles that contain words begin with 'demo,' such as 'demographic', 'democratic'.)
  6. If search terms are entered without quotes, they are treated as if a logical 'OR' was placed between each term. For example, a search for 'Public Health Malaysia' will return faculty profiles that contain the individual words 'Public' and/or 'Health' and/or 'Malaysia.'
  • Quickly enter the first few letters of the faculty last name. Select the faculty name you are searching for from the result list.