Calculating Motion Fields from Images with Two Different Exposure Times

In this paper, we present an extension to optical flow for estimating dense 2D motion fields with occlusion information. While optical flow computation is based on two consecutive short-exposure images, we make also use of an additional intermediate long-exposure image. This motion-blurred intermediate image captures scene motion directly. We introduce an image formation model that relates the long-exposure image to both short-exposure images in terms of dense 2D motion and local occlusion/disocclusion. Based on this image formation model, we describe a practical algorithm that enables estimating the 2D motion field of occluding and occluded regions as well as determining the instant of occlusion. Results for synthetic and real scenes demonstrate the validity of the proposed approach.