Tali Dekel


tdekel@google.com | talidekel@csail.mit.edu | talibasha@gmail.com

[Curriculum Vitae]

 
I'm a Research Scientist at Google, Cambridge. Before that I was a Postdoctoral Associate with Prof. Bill Freeman, at CSAIL, MIT.
I completed my Ph.D. in the school of Electrical Engineering of Tel-Aviv University, where I was supervised by Prof. Shai Avidan (TAU) and Prof. Yael Moses (IDC). My main research interests include images and videos analysis, multi-view systems, 3D structure and motion estimation, image synthesize and rendering.
 
 
News
 
   
 
Publications
 
 

MoSculp: Interactive Visualization of Shape and Time
Xiuming Xhang, Tali Dekel, Tianfan Xue, Andrew Owen, Jiajun Wu, Stefanie Mueller, William T. Freeman
ACM symposium on User interface software and technology (UIST), 2018
[paper][project]

Looking to Listen at the Cocktail Party: A Speaker-Independent Audio-Visual Model for Speech Separation
Ariel Ephrat, Inbar Mosseri, Oran Lang, Tali Dekel, Kevin Wilson, Avinatan Hassidim, Bill Freeman, Michael Rubinstein
ACM Transactions on Graphics (TOG). Proc. SIGGRAPH 2018
[paper] [project]

Sparse, Smart Contours to Represent and Edit Images
Tali Dekel, Chunag Gan. Dilip Krishnan, Ce Liu, William T. Freeman
Conference on Computer Vision and Pattren Recongnition (CVPR) 2018
[paper] [project]

Modifying Non-Local Variations Across Multiple Views
Tal Tlusty, Tomer Michaeli, Tali Dekel, Lihi Zelnik-Manor
Conference on Computer Vision and Pattren Recongnition (CVPR) 2018
[paper] [project]     

On The Effectiveness of Visible Watermarks
Tali Dekel, Michael Rubinstein, Ce Liu, William T. Freeman
Conference on Computer Vision and Pattren Recongnition (CVPR) 2017
[paper] [project]

Deviation Magnification: Revealing Departures from Ideal Geometries
Neal Wadhwa, Tali Dekel, Donglai Wei, Frédo Durand, William T. Freeman
ACM Transactions on Graphics (TOG). Proc. SIGGRAPH Asia  2015
[paper] [project]

Revealing & Modifying Non-Local Variations in a Single Image
Tali Dekel, Tomer Michaeli, Michal Irani, William T. Freeman
ACM Transactions on Graphics (TOG). Proc. SIGGRAPH Asia  2015
[paper] [project]
Best-Buddies Similarity for Robust Template Matching
Tali Dekel, Shaul Oron, Michael Rubinstein, Shai Avidan, William T. Freeman
Conference on Computer Vision and Pattren Recognition (CVPR) 2015
[paper] [project]
Space-Time Tradeoffs in Photo Sequencing
Tali Dekel
, Shai Avidan, Yael Moses
International Conference on Computer Vision (ICCV) 2013
[paper] [project]
Photo-Sequencing
Tali Dekel (Basha), Shai Avidan, Yael Moses
Oral in European Conference on Computer Vision (ECCV) 2012
[paper] [project]
Racing Bib Number Recognition
Idan Ben-Ami, Tali Dekel (Basha), Shai Avidan
British Machine Vision Conference (BMVC) 2012
[paper] [project]
Structure and Motion from Scene Registration
Tali Dekel (Basha), Shai Avidan, Alexander Hornung, Wojciech Matusik
Conference on Computer Vision and Pattren Recognition (CVPR) 2012
[paper] [project]
snowman snowman_D
Geometrically Consistent Stereo Seam Carving
Tali Dekel (Basha), Shai Avidan, Yael Moses
Oral in International Conference on Computer Vision (ICCV) 2011
[paper] [project]
ball_u ball_v
Multi-View Scene Flow Estimation: A View Centered Variational Approach
Tali Dekel (Basha), Yael Moses, Nahum Kiryati
Conference on Computer Vision and Pattren Recognition (CVPR) 2010
[paper] [project]
Ph.D. Thesis

From Camera-Array to CrowdCam
Tali Dekel


Journals

Best-Buddies Similarity - Robust Template Matching using Mutual Nearest Neighbors
Shaul Oron, Tali Dekel, Tianfan Xue, Shai Avidan, William T. Freeman
Transactions on Pattern Analysis and Machine Intelligence (TPAMI) 2017
[paper] [project]

Photo Sequencing
Tali Dekel (Basha), Yael Moses, Shai Avidan
International Journal of Computer Vision (IJCV) 2014
[paper] [project]
Stereo Seam Carving: A Geometrically Consistent Approach
Tali Dekel (Basha), Yael Moses, Shai Avidan
Transactions on Pattern Analysis and Machine Intelligence (TPAMI) 2013
[paper] [project]
Multi-View Scene Flow Estimation: A View Centered Variational Approach
Tali Dekel (Basha), Yael Moses, Nahum Kiryati
International Journal of Computer Vision (IJCV) 2013
[paper] [project]

Recent Talks