Liad Pollak | Temporal Super-Resolution using Deep Internal Learning
Details
Join Zoom Meeting
https://zoom.us/j/6043600514?pwd=VTFuU2VSTTNhTE1RRFJTZjhZNTN1Zz09
Meeting ID: 604 360 0514
Password: 703769
Abstract:
When a very fast dynamic event is recorded with a low frame rate camera, the resulting video suffers from severe motion blur and motion aliasing. Temporal Super-Resolution (TSR) recovers new high temporal frequencies beyond the temporal nyquist limit of the input video, thus resolving those effects. In this work we propose a "Deep Internal Learning" approach for true TSR. We train a video-specific CNN on examples extracted directly from the low frame rate input video. Our method exploits the strong recurrence of small space-time patches inside a single video sequence, both within and across different spatio-temporal scales of the video.
Bio:
Liad Pollak Zuckerman is a Machine Learning Applied Researcher at General Motors. Liad holds a B.Sc in EE & Physics from the Technion and an M.Sc in Computer Science from Weizmann Institute.