Thesis Defense: Removing motion blur from photographs
Speaker: Taeg Sang Cho , MIT CSAIL
Date: August 12 2010
Time: 11:00AM to 12:00AM
Location: Haus room (36-428)
Host: William T. Freeman, MIT CSAIL
Contact: Taeg Sang Cho, taegsang@mit.edu
Relevant URL: Abstract:
One of the long-standing challenges in photography is motion blur. For more than half a century, researchers have strived to remove blur computationally, but this problem is still considered unsolved. Blur removal is challenging because we need to (i) estimate how the image is blurred (i.e. the blur kernel or the point-spread function) and (ii) restore a natural looking image through deconvolution.
In this dissertation, we address a few aspects of these challenges. We introduce a new insight that a camera-shake blur kernel can be estimated by analyzing edges in a blurred photograph. Edge profiles in a blurred image encode projections of the blur kernel, from which we restore the blur kernel using the inverse Radon transform. We also develop an adaptive deconvolution technique tailored to improving renditions of texture in restored images. Subject motion can also cause blur, but in a spatially-varying manner. We address a restricted class of subject motion blur: the subject moves at a constant velocity locally. We design a new computational camera that improves the local motion estimation and, at the same time, reduces the image information loss due to blur.
Thesis Advisor: Prof. William T. Freeman
Thesis Committee: Prof. Fredo Durand and Dr. Richard Szeliski
See other events that are part of
See other events happening in August 2010
