Alexei (Alyosha) Efros

Adjunct Associate Professor
The Robotics Institute
and Computer Science Department
School of Computer Science
Carnegie Mellon University
Pittsburgh, PA 15213, USA

Office: 225 Smith Hall
Phone: +1 (412) 268-1234
Email: efr...@cs.cmu.edu


After a wonderful decade at CMU, I have moved the the EECS Department at UC Berkeley in Fall 2013. Please visit my new web page.

I am originally from St. Petersburg, Russia, but, due to some mixup at the travel agency, I now live in Pittsburgh, USA. I got my PhD from UC Berkeley in 2003 under the supervision of Jitendra Malik. I then spent a year as a fine fellow in lovely Oxford, working with Andrew Zisserman and the Visual Geometry Group. Since 2004, I am faculty at CMU with a joint appointment in the Robotics Institute and CS Department (and a courtesy appointment in Machine Learning Department). I am a member of the CMU Computer Vision Group and the CMU Graphics Lab, and also have close collaboration with the WILLOW Lab at INRIA/ENS in Paris.

Here is a slightly more official bio.

Research

Antonio Torralba and I are guest-editing an IJCV special issue on Big Visual Data. Submission Deadline: extended to May 31.

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 visual data, now called "Big Data", are readily available (see my recent talk on "What Makes Big Visual Data Hard?"). 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 group's research:

  • Qualitative Reasoning for Image Understanding: 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 be able to qualitativly capture scene properties such as geometric layout, occlusion relationships, camera viewpoint, scale, illumination, geographic properties, etc. But more than that, the goal is to capture the overall qualitative sense of the scene. For an overview, see my recent keynote lecture at BMVC'09.

  • Building the "Visual Memex": What could you do with a billion images? Can this vast heap of data be organized without loosing its representation power? Taking inspiration from Vannevar Bush's memex, our aim is to utilize the huge amount of existing visual data to discover links and connections between all visual elements, i.e. a giant multi-graph. Once constructed, the visual memex can be used to "explain" novel visual signal not in terms of hard categories ("car", "chair", "city"), but rather in terms of what has been seen before. Rather than asking "What is this?", we'd like to ask "What is this like?". For an overview, see my recent presentation and representative publications: Malisiewicz'08, Malisiewicz'09, Hays'08, Russell'09, Malisiewicz'11, Shrivastava'11.

  • Understanding (and Faking) Visual Realism: Why is it that most 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. Representative publications: Lalonde'07, Lalonde'07b, Hays'07, Lalonde'09.

Postdocs

Graduate Students

Former PhD Students

Former Postdocs

Teaching

Selected Projects

List of all my publications is also available on Google Scholar.
What makes Paris look like Paris?
Carl Doersch, Saurabh Singh, Abhinav Gupta, Josef Sivic, Alexei A. Efros
in SIGGRAPH 2012
Source code available
Watch the video
Unsupervised Discovery of Mid-Level Discriminative Patches
Saurabh Singh, Abhinav Gupta, Alexei A. Efros
in ECCV 2012
Source code available
People Watching: Human Actions as a Cue for Single View Geometry
David Fouhey, Vincent Delaitre, Abhinav Gupta, Alexei A. Efros, Ivan Laptev, Josef Sivic
in ECCV 2012
Watch the video
Scene Semantics from Long-term Observation of People
Vincent Delaitre, David Fouhey, Ivan Laptev, Josef Sivic Abhinav Gupta, Alexei A. Efros
in ECCV 2012
Dating Historical Color Images
Frank Palermo, James Hays, Alexei A. Efros
in ECCV 2012
Partial source code available
Undoing the Damage of Dataset Bias
Aditya Khosla, Tinghui Zhou, Tomasz Malisiewicz, Alexei A. Efros, Antonio Torralba
in ECCV 2012
Connecting Missing Links: Object Discovery from Sparse Observations using 5 Million Product Images
Hongwen (Henry) Kang, Martial Hebert, Alexei A. Efros, Takeo Kanade
in ECCV 2012
Object Instance Sharing by Enhanced Bounding Box Correspondence
Santosh Divvala, Alexei A. Efros, Martial Hebert
in BMVC'12
How important are Deformable Parts in the Deformable Parts Model?
Santosh Divvala, Alexei A. Efros, Martial Hebert
Parts and Attributes Workshop (at ECCV'12)
Data-driven Visual Similarity for Cross-domain Image Matching
Abhinav Shrivastava, Tomasz Malisiewicz, Abhinav Gupta, Alexei A. Efros
in SIGGRAPH Asia 2011
Watch the video
Ensemble of Exemplar-SVMs for Object Detection and Beyond
Tomasz Malisiewicz, Abhinav Gupta, Alexei A. Efros
in ICCV 2011
Source code available
ICML'12 invited applications talk (see Extended Abstract)
From 3D Scene Geometry to Human Workspace
Abhinav Gupta, Scott Satkin, Alexei A. Efros, Martial Hebert
in CVPR 2011
Watch video
Unbiased Look at Dataset Bias
Antonio Torralba, Alexei A. Efros
in CVPR 2011
Blocks World Revisited: Image Understanding using Qualitative Geometry and Mechanics
Abhinav Gupta, Alexei A. Efros, Martial Hebert
in ECCV 2010
ECCV Best Paper Honorable Mention
Source code available
Detecting Ground Shadows in Outdoor Consumer Photographs
Jean-François Lalonde, Alexei A. Efros, Srinivasa G. Narasimhan
in ECCV 2010
Source code available
Beyond Categories: The Visual Memex Model for Reasoning About Object Relationships
Tomasz Malisiewicz, Alexei A. Efros
in NIPS 2009.
Segmenting Scenes by Matching Image Composites
Bryan Russell, Alexei A. Efros, Josef Sivic, Bill Freeman, Andrew Zisserman
in NIPS 2009
Source code available
Webcam Clip Art: Appearance and Illuminant Transfer from Time-lapse Sequences
Jean-François Lalonde, Alexei A. Efros, Srinivasa G. Narasimhan
in SIGGRAPH Asia 2009
Source code available
Watch the video
Image Composition for Object Pop-out
Hongwen (Henry) Kang, Alexei A. Efros, Takeo Kanade, Martial Hebert
Workshop on 3D Representation for Recognition (3dRR-09) (at ICCV 2009)
Estimating Natural Illumination from a Single Outdoor Image
Jean-François Lalonde, Alexei A. Efros, Srinivasa G. Narasimhan
in ICCV 2009
(see expanded journal version in IJCV 2012)
Source code available
Image Sequence Geolocation with Human Travel Priors
Evangelos Kalogerakis, Olga Vesselova, James Hays, Alexei A. Efros, Aaron Hertzmann
in ICCV 2009
An Empirical Study of Context in Object Detection
Santosh Kumar Divvala, Derek Hoiem, James Hays, Alexei A. Efros, Martial Hebert
in CVPR 2009
What Does the Sky Tell Us About the Camera?
Jean-François Lalonde, Srinivasa G. Narasimhan, Alexei A. Efros.
in ECCV 2008
(see expanded journal version, IJCV 2009)
Source code available
Can Similar Scenes help Surface Layout Estimation?
Santosh Kumar Divvala, Alexei A. Efros, Martial Hebert
in IEEE Workshop on Internet Vision (at CVPR'08)
Recognition by Association via Learning Per-exemplar Distances
Tomasz Malisiewicz, Alexei A. Efros
in CVPR 2008.
Source code available
im2gps: estimating geographic information from a single image
James Hays, Alexei A. Efros
in CVPR 2008.
Flickr download code available
See interview with Hays on Pittsburgh TV station. And another one.
Closing the Loop on Scene Interpretation
Derek Hoiem, Alexei A. Efros, Martial Hebert
in CVPR 2008.
See 3D reconstruction compared to Photo Pop-up and Make3D
Image-based Shaving
Minh Hoai Nguyen, Jean-François Lalonde, Alexei A. Efros, Fernando de la Torre
in Eurographics 2008.
Recovering Occlusion Boundaries from a Single Image
Derek Hoiem, Andrew Stein, Alexei A. Efros, Martial Hebert
in ICCV 2007.
(see expanded journal version in IJCV 2011)
Source code available
Using Color Compatibility for Assessing Image Realism
Jean-François Lalonde, Alexei A. Efros
in ICCV 2007.
Improving Spatial Support for Objects via Multiple Segmentations
Tomasz Malisiewicz, Alexei A. Efros
in BMVC 2007.
Scene Completion using Millions of Photographs
James Hays, Alexei A. Efros
in SIGGRAPH 2007.
Flickr download code available
See article on BBC News
See also Communications of the ACM article with forward by Marc Levoy
Photo Clip Art
Jean-François Lalonde, Derek Hoiem, Alexei Efros, Carsten Rother, John Winn, Antonio Criminisi
in SIGGRAPH 2007.
Try the Live Java Demo
Watch the video
Putting Objects in Perspective
Derek Hoiem, Alexei A. Efros, Martial Hebert
In CVPR 2006.
Source code available
CVPR Best Paper Award
(see also expanded journal version, IJCV 2008)
Using Multiple Segmentations to Discover Objects and their Extent in Image Collections
Bryan Russell, Alexei A. Efros, Josef Sivic, Bill Freeman, Andrew Zisserman
in CVPR 2006
Source code available
Discovering Texture Regularity as a Higher-Order Correspondence Problem
James Hays, Marius Leordeanu, Alexei A. Efros, Yanxi Liu
in ECCV 2006
Source code available upon request.
Geometric Context from a Single Image
Derek Hoiem, Alexei A. Efros, Martial Hebert
In ICCV 2005
(see also expanded journal version, IJCV 2007)
Executable available (for non-commerical use only)
Discovering Objects and thier Location in Images
Josef Sivic, Bryan Russell, Alexei A. Efros, Andrew Zisserman, Bill Freeman
In ICCV 2005
Automatic Photo Pop-up
Derek Hoiem, Alexei A. Efros, Martial Hebert
In SIGGRAPH 2005
See article in The Economist
A Data-Driven Approach to Quantifying Natural Human Motion
Liu Ren, Alton Patrick, Alexei A. Efros, Jessica Hodgins. James Rehg.
In SIGGRAPH 2005
Seeing Through Water
Alexei A. Efros, Volkan Isler, Jianbo Shi, Mirko Visontai
In NIPS 17, 2004
Data available as frames or video
Recovering Human Body Configurations: Combining Segmentation and Recognition
Greg Mori, Xiaofeng Ren, Alexei A. Efros, Jitendra Malik
In CVPR 2004
Recognizing Action at a Distance
Alexei A. Efros, Alexander Berg, Greg Mori, Jitendra Malik
In ICCV 2003
Image Quilting for Texture Synthesis and Transfer
Alexei A. Efros, Bill Freeman
In SIGGRAPH 2001
Source code available
Texture Synthesis by Non-parametric Sampling
Alexei A. Efros, Thomas Leung
In ICCV 1999

Funding Sources

Curriculum Vitae

Misc.

Free web counters
since Jan 2007.