Motion blur retains some information about motion, based on which motion may be recovered from blurred images. This is a difficult problem, as the situations of motion blur can be quite complicated, such as they may be space variant, nonlinear, and local. This paper addresses a very challenging problem: can we recover motion blindly from a single motion-blurred image?
There are mainly three contributions in our work
- Motion blur constraint: a major contribution of this paper is a new finding of an elegant motion blur constraint. Exhibiting a very similar mathematical form as the optical flow constraint, this linear constraint applies locally to pixels in the image. An illustration example is shown in Fig. 1.
- Space-variant motion blur estimation: a number of challenging problems can be addressed under a unified framework, including:
- Motion blur estimation with a global parametric form, such as affine and rotational motion blur,
- Multiple motion blur patterns estimation and segmentation,
- Nonparametric motion blur field estimation.
- Applications:
- Space-variant motion deblurring with a modified Richardson-Lucy algorithm,
- Blur/motion synthesis.
