Anat Levin


MIT CSAIL
The Stata Center 32-D466
32 Vassar Street, Cambridge MA 02139
Phone: +617-253-7245

E-mail :

Vita



Research Interests:

My research interests are in the areas of Computer Vision, Computer Graphics and Machine Learning. In particular I worked on low and mid level vision, computational photography, inference and optimization, and visual recognition and detection. For more details about my work, please have a look at my publications list.



Publications:
 

Anat Levin, Peter Sand, Taeg Sang Cho, Fredo Durand, William T. Freeman. Motion-Invariant Photography.
SIGGRAPH, ACM Transactions on Graphics, Aug 2008.
Hi-res PDF  Low-res PDF  Supplemental Results

Anat Levin, William T. Freeman, Fredo Durand. Understanding camera trade-offs through a Bayesian analysis of light field projections.
CSAIL Tech Report, April 2008.
PDF

Anat Levin, Rob Fergus, Fredo Durand, William T. Freeman. Image and Depth from a Conventional Camera with a Coded Aperture.
SIGGRAPH, ACM Transactions on Graphics, Aug 2007.
PDF  Project Page

Anat Levin, Alex Rav-Acha, Dani Lischinski. Spectral Matting.
Best paper award runner up.
IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), Minneapolis, June 2007
PDF  Extended TR  Slides  Project Page (Including ground truth matting evaluation data)

A. Levin D. Lischinski and Y. Weiss. A Closed Form Solution to Natural Image Matting.
IEEE Trans. Pattern Analysis and Machine Intelligence, Feb 2008
PDF

A. Levin and Y. Weiss. User Assisted Separation of Reflections from a Single Image Using a Sparsity Prior.
IEEE Trans. Pattern Analysis and Machine Intelligence, Sep 2007
PDF

A. Levin. Blind Motion Deblurring Using Image Statistics.
Advances in Neural Information Processing Systems (NIPS), Dec 2006
PDF  Images

A. Levin D. Lischinski and Y. Weiss. A Closed Form Solution to Natural Image Matting.
IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), June 2006, New York
PDF  Extended Version (To Appear in PAMI)  Slides  Code&Images

A. Levin and Y. Weiss. Learning to Combine Bottom-Up and Top-Down Segmentation.
Longuet-Higgins best paper award.
Proc. of the European Conference on Computer Vision (ECCV), Graz, Austria, May 2006.
PDF (modified from the proceeding version)  Slides

A. Levin D. Lischinski and Y. Weiss Colorization using Optimization.
SIGGRAPH, ACM Transactions on Graphics, Aug 2004.
Results Page + Code  This page has recently been slashdotted!
PS  PDF  Slides

A. Levin and R. Szeliski Visual Odometry and Map Correlation.
IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), June 2004, Washington DC
PS  PDF

A. Levin, A. Zomet and Y. Weiss Separating Reflections from a Single Image Using Local Features.
IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), June 2004, Washington DC
PS  PDF

A. Levin and Y. Weiss. User Assisted Separation of Reflections from a Single Image Using a Sparsity Prior.
Proc. of the European Conference on Computer Vision (ECCV), Prague, May 2004.
Abstract  PS  PDF  Code&Images(Last modified: Sep 13, 2004)

A. Levin, A. Zomet, S. Peleg and Y. Weiss. Seamless Image Stitching in the Gradient Domain.
Proc. of the European Conference on Computer Vision (ECCV), Prague, May 2004.
Abstract   PDF

A. Levin, A. Zomet, S. Peleg and Y. Weiss. Seamless Image Stitching in the Gradient Domain.
Hebrew University Technical Report, 2003-82.
Abstract   PDF

A. Levin, A. Zomet and Y. Weiss. Learning How to Inpaint from Global Image Statistics.
International Conference on Computer Vision (ICCV), Oct 2003, Nice, France.
Abstract  PS  PDF

A. Levin, P. Viola and Y. Freund. Unsupervised Improvement of Visual Detectors using Co-Training.
International Conference on Computer Vision (ICCV), Oct 2003, Nice, France.
Abstract  PS  PDF

A. Levin, A. Zomet and Y. Weiss. Learning to Perceive Transparency from the Statistics of Natural Scenes.
Finalist for the Ben Wegbreit best student paper award.
Advances in Neural Information Processing Systems (NIPS) Dec 2002, Vancouver, Canada.
Abstract  PDF

A. Shashua and A. Levin. Ranking with Large Margin Principle: Two Approaches.
Advances in Neural Information Processing Systems (NIPS) Dec 2002, Vancouver, Canada.
Abstract  PS  PDF

A. Levin and A. Shashua Principal Component Analysis Over Continuous Subspaces and Intersection of Half-spaces.
Proc. of the European Conference on Computer Vision (ECCV), May 2002,Copenhagen, Denmark.
Abstract  PS  PDF

A. Levin and A. Shashua Revisiting Single-view Shape Tensors: Theory and Applications.
Proc. of the European Conference on Computer Vision (ECCV), May 2002,Copenhagen, Denmark.
Abstract  PS  PDF

A. Shashua A. Levin and S. Avidan Manifold Pursuit: A New Approach to Appearance Based Recognition.
Proc. of the Int. Conf. on Pattern Recog. (ICPR), Aug 2002, Quebec City, Canada.
Abstract  PS  PDF

A. Shashua, R. Meshulam, L. Wolf, A. Levin and G. Kalai. On Representation Theory in Computer Vision Problems. Technical Report 2002-44, Leibniz Center for Research, School of Computer Science and Eng., The Hebrew University of Jerusalem, July, 2002
Abstract  PDF

A. Shashua and A. Levin Linear Image Coding for Regression and Classification using the Tensor-rank Principle.
IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), Dec 2001, Hawaii.
Abstract  PS  PDF

A. Levin L. Wolf and A. Shashua Time-varing Shape Tensors for Scenes with Multiply Moving Points.
IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), Dec 2001, Hawaii.
Abstract  PS  PDF

A. Shashua and A. Levin Multi-frame Infinitesimal Motion Model for the Reconstruction of (Dynamic) Scenes with Multiple Linearly Moving Objects. International Conference on Computer Vision (ICCV), July 2001, Vancouver, Canada.
Abstract  PS  PDF