Eli Shechtman
Senior Research Scientist

I am a researcher at the Adobe Creative Technologies Lab. My research interests are in the areas of computer vision and computer graphics. More specifically I am interested in non-parametric and by-example methods for image and video synthesis and analysis. In my recent work I explored how local similarities within and across images and video can be used for image editing, enhancement, interpolation, object and action recognition, visual saliency, video summarization and more.

I finished my B.Sc. in Electrical Engineering (cum laude) from Tel-Aviv University in 1996. Between 2001 and 2007 I attended the Weizmann Institute of Science where I received with honors a M.Sc. and Ph.D in Applied Mathematics and Computer Science. I had the honor to be advised by Prof. Michal Irani. More details about my Ph.D. work can be found here. During that time I also worked as a computer vision researcher in Elop. In August 2007 I joined Adobe and also started sharing my time as a post-doc with the University of Washington’s Computer Science & Engineering department. Since 2010 I am a full researcher at the Creative Technologies Lab.

projects

Patch based analysis and synthesis:

• (New!) Non Rigid Dense Correspondence
• Video Tapestries
• Regenerative Morphing
• PatchMatch
• Bidirectional Similarity
• Space-Time Video Completion

Faces:

• (New!) Exploring Photobios
• (New!) Expression Flow
• Being John Malkovich

Content analysis:

• Cosaliency
• Naive Bayes Nearest Neighbor Classification
• Matching Local Self-Similarities
• Actions as Space-Time Shapes
• Space-Time Behavioral Correlation

Other:

• Space-Time Super-Resolution

tech transfers

• Content Aware Fill in Photoshop CS5 and Content Aware Spot Healing Brush in PSE9

Publications

• Yoav HaCohen, Eli Shechtman, Dan B Goldman, Dani Lischinski. 2011. Non-Rigid Dense Correspondence with Applications for Image Enhancement. ACM Transactions on Graphics (SIGGRAPH), 30(4). (to appear)
• Ira Kemelmacher-Shlizerman, Eli Shechtman, Rahul Garg, Steven M. Seitz. 2011. Exploring Photobios. ACM Transactions on Graphics (SIGGRAPH), 30(4). (to appear)
• Fei Yang, Jue Wang, Eli Shechtman, Lubomir Bourdev, Dimitri Metaxas. 2011. Expression Flow
  for 3D-Aware Face Component Transfer. ACM Transactions on Graphics (SIGGRAPH), 30(4). (to appear)
• David E. Jacobs, Dan B Goldman, and Eli Shechtman. 2010. Cosaliency: where people look when comparing images. In Proceedings of the 23nd annual ACM symposium on User interface software and technology (UIST '10). ACM, New York, NY, USA, 219-228. 
• Ira Kemelmacher-Shlizerman, Aditya Sankar, Eli Shechtman, Steven M. Seitz. 2010. Being John Malkovich. European Conference on Computer Vision (ECCV), Crete.
• Connelly Barnes, Eli Shechtman, Dan B Goldman, Adam Finkelstein. 2010. The Generalized PatchMatch Correspondence Algorithm. European Conference on Computer Vision . European Conference on Computer Vision (ECCV), Crete.
• Connelly Barnes, Dan B Goldman, Eli Shechtman, Adam Finkelstein. 2010. Video Tapestries with Continuous Temporal Zoom. ACM Transactions on Graphics (Proc. SIGGRAPH), 29(3).
• Eli Shechtman, Alex Rav-Acha, Michal Irani, Steven M. Seitz. 2010. Regenerative Morphing. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), San-Francisco.
• Connelly Barnes, Eli Shechtman, Adam Finkelstein, Dan B Goldman. 2009. PatchMatch: A Randomized Correspondence Algorithm for Structural Image Editing. ACM Transactions on Graphics (Proc. SIGGRAPH), 28(3).
• Oren Boiman, Eli Shechtman, Michal Irani. 2008. In Defense of Nearest-Neighbor Based Image Classification. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Anchorage.
• Denis Simakov, Yaron Caspi, Eli Shechtman, Michal Irani. 2008. Summarizing Visual Data Using Bidirectional Similarity. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR).
• Lena Gorelick, Moshe Blank, Eli Shechtman, Michal Irani, Ronen Basri. 2007. Actions as Space-Time Shapes. In IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI).
• Eli Shechtman and Michal  Irani. 2007.  Space-time behavior based correlation – OR – How to tell if two underlying motion fields are similar without computing them?   In IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI).
• Yonatan Wexler, Eli Shechtman, Michal Irani, 2007. Space-Time Completion of Video .  In IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI).
• Eli Shechtman and Michal Irani. 2007. Matching Local Self-Similarities across Images and Videos.   IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Minneapolis.
• Moshe Blank, Lena Gorelick, Eli Shechtman, Michal Irani, Ronen  Basri. 2005. Actions as Space-Time Shapes.   International Conference on Computer Vision (ICCV), Beijing.
• Eli Shechtman, and Michal Irani. 2005. Space-Time Behavioral Correlation. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), San-Diego.
• Eli Shechtman, Yaron Caspi, Michal Irani. 2004.  Space-Time Super-Resolution.   In IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI).
• Yonatan Wexler, Eli Shechtman, Michal Irani. 2004. Space-Time Video Completion.   IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Washington DC. Received a Best Poster award at CVPR'04.
• Eli Shechtman, Yaron Caspi, Michal Irani. 2002. Increasing Space-Time Resolution in Video.   European Conference on Computer Vision (ECCV), Copenhagen. Received the Best Paper Prize at ECCV'02.

My previous publications and projects can be found in my Weizmann homepage.

honors

---

• 2007 – The J.F. Kennedy Award for Ph.D. work (highest award), Weizmann Institute of Science
• 2007 – Outstanding Student Award, The Israeli Knesset (parliament)
• 2004 – Best Poster Award, CVPR 2004, for the paper “Space-Time Video Completion”
• 2003 – Dean's prize for M.Sc. students, Weizmann Institute of Science
• 2002 – Best Paper Award, ECCV 2002, for the paper “Increasing Space Time Super-Resolution in Video”