Pictures are taken from the paper “Invertible motion Blur in Video" by Amit Agrawal_ Yi Xu, Ramesh Raskar
The project deals with motion deblurring in successive video frames. The blur can be invertible even if the point-spread function (PSF) due to motion smear in a single photo is non-invertible. The key idea is to record the same object with varying PSFs, so that the nulls in the frequency component of one frame can be filled by other frames. The combined frequency transform becomes null-free, making deblurring well-posed. We will achieve jointly-invertible blur simply by changing the exposure time of successive frames. The problem of automatic deblurring of objects moving with constant velocity consist of solving four critical components: preservation of all spatial frequencies, segmentation of moving parts, motion estimation of moving parts, and non-degradation of the static parts of the scene.
In this project we will implement the paper and try to improve it in its weakness points.