Tavi HalperinComputer Vision and Deep Learning Researcher @ Lightricks
Google Scholar | Linkedin | Github
This is an outdated page. My new homepage can be found here.
Researcher and team lead at the research department at Lightricks. My focus is on
state-of-the-art algorithms and neural networks that can also run on mobile
devices. Specifically interested in video processing.
Previously, I did a Phd in Computer Science at the Hebrew University of Jerusalem. My thesis was about video processing, geometry, and using deep learning to jointly learn from audio and video. My advisor was Prof. Shmuel Peleg.
Endless Loops: Detecting and Animating Periodic Patterns in Still Images
ACM Transactions on Graphics (Proc. SIGGRAPH), 2021
Egosampling: Wide view hyperlapse from egocentric videos
IEEE Transactions on Circuits and Systems for Video Technology (TCSVT) 2017
Epipolar geometry based on line similarity
International Conference on Pattern Recognition (ICPR) 2016
Method and system for enhancing a speech signal of a human speaker in a video using visual information
Method and system for generating adaptive fast forward of egocentric videos