RI | People | Alexei A. Efros

Text only version of this site

Alexei A. Efros
Assistant Professor, RI/CS

Email address: efros@cs.cmu.edu

Mailing address:
Carnegie Mellon University
Robotics Institute
5000 Forbes Avenue
Pittsburgh, PA 15213

For more information, see my personal homepage.

Jump to: Research interests | Keywords | Labs & groups | Projects | Publications

Research interests

My research is in the area of computer vision and computer graphics, especially at the intersection of the two. I am 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. The ultimate goal is to use the ever-growing amount of stored visual information (digital photo albums, webcams, movies, etc.) to learn, understand, and resynthesize the visual world around us.

In very broad strokes, here are the main current themes of my research:

• Qualitative 3D Reasoning for Image Interpretation: The ability to see and understand the three-dimensional world behind a two-dimensional image goes to the very heart of the computer vision problem. The overall objective of this research effort is, given a single image, to automatically produce a coherent interpretation of the depicted scene. On one level, such interpretation should include opportunistically recognizing known objects (e.g. people, houses, cars, trees) and known materials (e.g. grass, sand, rock, foliage) as well as their rough positions and orientations within the scene. But more than that, the goal is to capture the overall qualitative sense of the scene.

• "Brute-forcing" Vision: What could you do with a billion images? Taking inspiration from Google -- the A.I. for the post-modern world -- we want to utilize the huge amount of existing visual data to "look-up" similar images as a cue to interpreting a previously unseen photograph. That is, we would like to sample from the entire space of scenes as a way of exhaustively modeling our visual world? If this works, it might allow us to "brute force" many currently unsolvable vision and graphics problems!

• Understanding (and Faking) Visual Realism: Why is it that most of computer-generated imagery doesn't look very realistic? What is it that the Renaissance artists knew that we don't? Which bits of the visual experience is it important to "get right", and which could be safely faked without anyone noticing? The ultimate goal is to make synthesized images appear as real and convincing as regular photographs.

Research interest keywords

computer graphics, computer vision, image processing, machine learning, and object recognition

Current Labs & Groups

Computer Graphics Lab - Modeling, animation, and rendering of 3-D scenes

Current Projects

Geometrically Coherent Image Interpretation - Understanding a 3D scene from a single image

Recent publications [View all 24 publications]

• Statistics of 3D object locations in images
  R. Baur, A.A. Efros, and M. Hebert
  tech. report CMU-RI-TR-08-43, Robotics Institute, Carnegie Mellon University, November, 2008. [Abstract]
  Download: pdf [10806 KB] copyrighted

• A Unified Approach for Detection, Classification and Segmentation
  D. Hoiem, S. Divvala, J.H. Hays, A.A. Efros, and M. Hebert
  European Conference on Computer Vision (ECCV) 2008, PASCAL VOC 2008 Workshop, October, 2008. [Abstract]
  Download: pdf [2025 KB] copyrighted

• Camera parameters estimation from hand-labelled sun positions in image sequences
  J. Lalonde, S.G. Narasimhan, and A.A. Efros
  tech. report CMU-RI-TR-08-32, Robotics Institute, Carnegie Mellon University, July, 2008. [Abstract]
  Download: pdf [326 KB] copyrighted

• Can Similar Scenes help Surface Layout Estimation?
  S. Divvala, A.A. Efros, and M. Hebert
  IEEE Workshop on Internet Vision, at CVPR'08, June, 2008. [Abstract]
  Download: pdf [7112 KB] copyrighted

• Closing the Loop on Scene Interpretation
  D. Hoiem, A.A. Efros, and M. Hebert
  Proc. Computer Vision and Pattern Recognition (CVPR), June, 2008.
  Download: pdf [5469 KB] copyrighted

• IM2GPS: estimating geographic information from a single image
  J.H. Hays and A.A. Efros
  Proc. Computer Vision and Pattern Recognition (CVPR), June, 2008. [Abstract]
  Download: pdf [11936 KB] copyrighted

• Recognition by Association via Learning Per-exemplar Distances
  T. Malisiewicz and A.A. Efros
  Proc. Computer Vision and Pattern Recognition (CVPR), June, 2008. [Abstract]
  Download: pdf [7859 KB] copyrighted

• Image-based Shaving
  M.H. Nguyen, J. Lalonde, A.A. Efros, and F. De la Torre Frade
  Computer Graphics Forum Journal (Eurographics), Vol. 27, No. 2, April, 2008, pp. 627 - 635. [Abstract]
  Download: pdf [5705 KB] copyrighted

• What does the sky tell us about the camera?
  J. Lalonde, S.G. Narasimhan, and A.A. Efros
  European Conference on Computer Vision, 2008. [Abstract]
  Download: pdf [2898 KB] copyrighted

• Recovering Occlusion Boundaries from a Single Image
  D. Hoiem, A. Stein, A.A. Efros, and M. Hebert
  International Conference on Computer Vision (ICCV), October, 2007. [Abstract]
  Download: pdf [2337 KB] copyrighted