Yoni Wexler's Home Page

 
 

Yonatan Wexler

Tel: +972-2-591-7800


firstname.lastname@orcam.com

I am heading the R&D of a new startup. My research interests lie in the field of Computer Vision, Geometry in Vision (Motion Analysis, Shape Description) for perceptual tasks such as Action Recognition, View Synthesis and Augmented Reality. My work has been concentrated particularly on the recovery and representation of scenes from images. My research focuses on finding computational methods that enable accurate and efficient use of pictorial data, both in images and video sequences.

 

Research

Detecting Text in Natural Scenes with Stroke Width Transform

Seamless montage for texturing models

 

Factoring repeated content within and among images

Space-Time Video Completion

 

Space-Time Scene Manifolds

   

 

Alpha Matting

 

Environment Matting

       

Qwarping

 

Dynamic Morphing

   

 

     

Publications

Detecting Text in Natural Scenes with Stroke Width Transform.
B. Epshtein, E. Ofek and Y. Wexler
Computer Vision and Pattern Recognition (CVPR) 2010

pdf


Seamless montage for texturing models.
R. Gal, Y. Wexler, E. Ofek, H. Hoppe and D. Cohen-Or.
Eurographics 2010

abstract, project page, pdf, supplemental material, optimizer animation.


Factoring repeated content within and among images.
H. Wang, Y. Wexler, E. Ofek, H. Hoppe.
ACM SIGGRAPH 2008,

abstract, pdf


Hierarchical photo organization using geo-relevance
B. Epshtein, E. Ofek, Y. Wexler and P. Zhang
ACM GIS 2007, Seattle, Washington.
abstract, pdf


Space-Time Scene Manifolds
Y. Wexler and D. Simakov
International Conference on Computer Vision (ICCV) 2005, abstract ,
pdf


Space-Time Video Completion
Y. Wexler, E. Shechtman, and M. Irani
In IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), March 2007. pdf.


Previously appeared in Computer Vision and Pattern Recognition (CVPR) 2004 and received Best Poster Award.  abstract, pdf


Image-Based Rendering Using Image-Based Priors
A.W. Fitzgibbon Y. Wexler, and A. Zisserman.
International Conference of Computer Vision (ICCV) 2003. Received the
David Marr Prize.
Abstract, pdf, Data
Also appeared in the International Journal of Computer Vision, 63(2):141–151, July 2005. Marr Prize special issue.

Learning Epipolar Geometry from Image Sequences
Y. Wexler, A.W. Fitzgibbon and A. Zisserman
IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), June 2003
abstract, pdf


Image-based Environment Matting
Y. Wexler, A. Fitzgibbon and A. Zisserman.
Proc. 13th Eurographics Workshop on Rendering, Italy, 2002.
pdf
Shorter version appeared as SIGGRAPH 02' sketch, San Antonio.
pdf


Bayesian Estimation of Layers from Multiple Images.
Y. Wexler, A. Fitzgibbon and A. Zisserman.
Proc. 7th European Conference on Computer Vision (ECCV), Copenhagen, Denmark, 2002.
ps.gz, pdf.


View Synthesis using Convex and Visual Hulls
Y. Wexler, R. Chellappa.
In Proc. British Machine Vision Conference 2001', Manchester.
pdf

Join Tensors: On 3D-to-3D Alignment of Dynamic Sets
L. Wolf, A. Shashua and Y. Wexler
Proc. of Int. Conf. on Pattern Recog. (ICPR), Sep. 2000, Barcelona.
pdf.
Also,
CfAR report 4097, January 2000: ps.gz pdf

On the Synthesis of Dynamic Scenes from Reference Views.
Y. Wexler and A. Shashua
IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), June 2000, South Carolina
CfAR report 4096, January 2000. ps.gz pdf
Sample output automatically builds
this movie from these 3 images.


Q-warping: Direct Computation of Quadratic Reference Surfaces.
Y. Wexler and A. Shashua.
IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), June 1999.
pdf
Also, PAMI journal version appeared in August 2001 (Vol. 23, No. 8, pp. 920-925)
pdf

 

 

Awards

The Marr Prize Best Paper Award at the 9th International Conference of Computer Vision (ICCV) 2003
Best Poster Award at the 22nd IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2004)
 
 

Places I have been affiliated with

Microsoft's Virtual Earth (now Bing Maps)

The Weizmann Institute of Science

Oxford University’s Visual Geometry Group

The University of Maryland, Center for Automation Research

The Hebrew University