Recovering ball motion from a single motion-blurred image

Motion blur often affects the ball image in photographs and video frames in many sports such as tennis, table tennis, squash and golf. In this work we operate on a single calibrated image depicting a moving ball over a known background, and show that motion blurred ball images, usually unwelcome in computer vision, bear more information than a sharp image. We provide techniques for extracting such information ranging from low-level image processing to 3D reconstruction, and present a number of experiments and possible applications, such as ball localization with speed and direction measurement from a single image, and ball trajectory reconstruction from a single long-exposure photograph.