Abstract

We present a method that utilizes bracket sequence images to automatically extract the alpha matte of a motion-blurred ob ject. This method makes use of a sharp, short-exposure snapshot in the sequence to help overcome ma jor challenges in this task, including blurred ob ject detection, spatially-variant ob ject motion, and foreground/background color ambiguity. A key component of our matte estimation is the infer- ence of approximate, spatially-varying motion of the blurred ob ject with the help of the sharp snapshot, as this motion information provides im- portant constraints on the aforementioned issues. In addition, we take advantage of other relationships that exist between a pair of consecutive short-exposure and long-exposure frames, such as common background areas and consistencies in foreground appearance. With this technique, we demonstrate successful alpha matting results on a variety of moving ob jects including non-rigid human motion.