An object which moves during the exposure time results in a blurred smear in the image. We consider the smear as if it was
the image of a semitransparent object, and we retrieve its alpha matte by means of known techniques. The alpha value at a
pixel is meaningfully interpreted as the fraction of the exposure time during which the object projection overlapped that
pixel.
Basing on this fact, our work highlights interesting qualitative and quantitative properties of the alpha matte, which can
be used to derive constraints on the object’s apparent contour, and its motion during the exposure time, from a single motion-blurred
image; we also show that some of these properties hold on the original image.
The theory is validated with experimental results both on synthetic and real images, highlighting strengths and limitations;
we point out a range of possible applications, including blurred image interpretation, temporal superresolution of object
contours, model-based reconstruction of nontrivial motion, and improvements of alpha matting techniques.
Keywords Motion blur - Alpha matting - Temporal superresolution - Finite exposure time